ANALYTIC MEASUREMENT OF ONLINE SOCIAL MEDIA CONTENT
A social media analytics platform including methods, apparatuses and computer-readable media for providing analytic measurements of online social media content by harvesting and aggregating unstructured qualitative online social media conversations relevant to subject matter of interest in a category from one or more online social media sources, quantifying the aggregated online social media conversations, and providing actionable information based on the quantified aggregated online social media conversations, the actionable information including sentiment expressed among online social media participants concerning subject matter of interest in the category.
Latest Buzzient, Inc. Patents:
- Modeling social networks using analytic measurements of online social media content
- WEBSITE NETWORK AND ADVERTISEMENT ANALYSIS USING ANALYTIC MEASUREMENT OF ONLINE SOCIAL MEDIA CONTENT
- Website network and advertisement analysis using analytic measurement of online social media content
- MODELING SOCIAL NETWORKS USING ANALYTIC MEASUREMENTS OF ONLINE SOCIAL MEDIA CONTENT
- WEBSITE NETWORK AND ADVERTISEMENT ANALYSIS USING ANALYTIC MEASUREMENT OF ONLINE SOCIAL MEDIA CONTENT
This application claims the benefit of U.S. provisional application No. 61/114,445, entitled “Aggregating and Presenting Quantitative Online Social Media Content,” filed on Nov. 13, 2008.
FIELD OF THE INVENTIONAt least certain embodiments of the invention relate generally to information management, and more particularly to providing analytic measurement of online social media content.
BACKGROUND OF THE INVENTIONTraditional methods of collecting, managing and providing real-time or near real-time relevant information have been enhanced through the use of the Internet and online research and information collection tools. One such set of tools is known as web analytics. Web analytics focus on a company's own website for collection of online information, particularly traffic data. Web analytics are limited because they only consider a subset of the relevant online universe, specifically the behavior of users of a given website. They do not discover other information about the users such as interests and opinions expressed in interactive systems. Behavioral analytics are another set of information collection and management tools that attempts to analyze the “click stream” of users and show advertisements based on this information. However, this method has many technical limitations since it tends to provide only a very limited picture of a user's overall interests. Also there is a lack of consolidation between a user's work and home PCs.
Online social media is a new source of valuable information on the Internet that may be harvested to generate information and other data about products or services, branding, competition, and industries. Online social media encompasses online media such as blogs and sub-blogs, online discussion forums, social networks, wiki sites such as Wikipedia, online reviews on e-commerce sites such as Amazon.com®, video sites such as YouTube®, micro-blogging services such as Twitter®, and so on. There are currently over 106 million blogs growing at a rate of 11% per year. There are several million forums with active contributions by more than 33% of Internet users. There are 483 million users of social networks worldwide growing at a rate of 47% annually. As a result, social media is becoming a crucial and rapidly growing source of consumer opinion. This information may allow users to quantify opinion on social media sites to gain useful insights into current consumer sentiment and trends relating to their products or services, brands, and/or technologies, and those of their competitors. Collecting and presenting this information can help users in a variety of ways such as, for example, target advertising revenues and expenditures, marketing, sales, customer service, brand management, product development, investor relations, and so on. Social networking sites are currently trying to leverage their own user profiles to target advertising based on their users' behavior and declared interests. However, most users today participate in several different online social media sites. Online content analytics are another set of information collection tools that attempts to analyze content in social media sites such as online forums, blogs, and so on. However, these techniques require a high degree of manual human intervention by analysts. Additionally, the reports generated by these analysts can be very expensive and can't be updated very frequently due to the necessity of human intervention in the data gathering and analysis process.
SUMMARY OF THE DESCRIPTIONAt least certain embodiments disclose a social media analytics platform for providing analytic measurements of online social media content by harvesting and aggregating unstructured qualitative online social media conversations relevant to subject matter of interest in a category from one or more online social media sources, quantifying the aggregated online social media conversations, and providing actionable information based on the quantified aggregated online social media conversations, the actionable information including sentiment expressed among online social media participants concerning subject matter of interest in the category.
A better understanding of at least certain embodiments of the invention can be obtained from the following detailed description in conjunction with the following drawings.
Throughout the description, for the purposes of explanation, numerous specific details are set forth in order to provide a thorough understanding of the present invention. It will be apparent to one skilled in the art, however, that the present invention may be practiced without some of these specific details. In other instances, well-known structures and devices are shown in block diagram form to avoid obscuring the underlying principles of embodiments of the invention.
At least certain embodiments disclose a social media analytics platform including methods, apparatuses, and computer-readable media for providing analytic measurements of online social media content by harvesting and aggregating unstructured qualitative online social media conversations relevant to subject matter of interest in a category from one or more online social media sources, quantifying the aggregated online social media conversations including performing statistical analysis on the conversations to obtain the analytical measurements of the online social media content, and providing actionable information based on the quantified aggregated online social media conversations, the actionable information including sentiment expressed among online social media participants concerning subject matter of interest in the category. The actionable information may be retrieved based on real-time measurements of the online social media sentiment expressed among the online social media participants. The actionable information may also be retrieved based on historical data representing quantitative measurements of the sentiment expressed among online social media participants in the past. Embodiments also assign a sentiment rating to each of the online social media conversations referring to the subject matter of interest. Embodiments then present the analytic measurements of the online social media content in a user interface in an intuitive and user-friendly manner at different levels of granularity that enables the quantified online social media content to be grouped and filtered in a variety of default and/or customizable ways. In one embodiment, the user interface is a web-based service. In alternative embodiments, the user interface may be provided as a browser-based interface hosted by a behind-the-firewall hardware or software appliance.
Embodiments provide analytic measurement of online social media content for users such as global enterprises, advertising agencies, sales and marketing departments, media companies, government agencies, and virtually any entity requiring real-time or near real-time access to such information. This online social media content is quantified and provided in a relevant and user-friendly manner to these entities using an interface such as a graphical user interface (GUI). These embodiments provide both historical and current measurements to enable analysis of past and present information. Online social media content is harvested, sorted, and provided to relevant groups or entities. Certain embodiments describe a social media analytics platform for collecting and converting raw online social media conversations into actionable information that can be used to increase the top-line growth and margins of its recipients. Additionally, this aggregation of social media information can be analyzed to determine trends in each of the above discussed categories.
Monitoring and aggregating this new information source may be used on its own or in conjunction with traditional research and measurements such as, for example, quantitative and qualitative market research, paid media tracking, and traditional web site analytics. This process is automated so that qualitative measurements can be aggregated, quantified, and presented with minimal human intervention. At least certain embodiments contemplate a harvesting process referred to herein as “scraping” where social media sources are discovered or located and exploited for relevant information. The content is then aggregated and quantified in a manner relevant to the industry or other category. The aggregated and quantified online social media content is then provided to the user of the social media analytics (SMA) platform in an efficient, timely and user-friendly manner using the interface. In one embodiment, the interface is user-specific.
Examples of the quantitative online social media content data that can be provided by embodiments include: brand and product/service sentiment for users and their competition; the share of voice of the brand (e.g., volume of discussion about the brand, product or service) over the social media versus the competition; topics and keywords used by online discussion participants for the brand and the competition; information on the opinion leaders for the category (e.g., online social content authors with the most influential voices); top websites resulting from the brand search; automated alerts for changes in sentiment; keywords, terms or phrases in posts to the online social media websites; and much more. This information is aggregated, quantified, and provided to users in real-time or near-real-time for the purpose of, for example, marketing, public relations, advertising, sales, customer service, brand management, product development, investor relations, and so on. The result of this process is to provide highly relevant and timely actionable information to users of the SMA platform.
This information may be advantageous for several reasons including brand and product/service perception or sentiment analysis, trend recognition and opportunity identification, early warnings about customer service or quality issues, opinion leader identification and engagement, competitor monitoring, and optimized online advertising to name a few. This information allows users to quantify opinion on social media sites to gain insights into current consumer sentiment about the users' products or services, brands, and technologies and those of their competitors. This information also enables users of the SMA platform to recognize trends in consumer buzz about new technologies, product or service types, and attributes. In addition, users may receive early-warning signs to identify dissatisfied customers. Users also may identify and target opinion leaders for a given product/service or category using this information. Embodiments of the SMA platform can also supplies users with a list of highly relevant websites where high-affinity users are exchanging opinions and making purchasing decisions. This information can also be made widely available inside users' organizations using an interface to push analytics to potentially everyone inside the organization instead of just the top-level marketing staff enabling entire organizations to establish an overall better sense of the voice of their customers and to make informed decisions at the customer level because embodiments focus on the social behavior of potential customers using online social media sources and provide far better insight into commercially relevant interests.
The harvesting layer 100 of
The vertical layer 300 stores the aggregated and quantified online social media content in a database and supplies the content to the presentation layer 700 for display. Presentation layer 700 of
At operation 203 the scraping process is performed including scouring the identified online social media sources for conversations relevant to a particular sector or other category and breaking down the content into pieces to be stored for later processing. The scraping process starts at an overview page typically provided by each social media source and identifies hyperlinks to potentially relevant subpages and content pages based on the structural properties of these hyperlinks. The process then iteratively drills down multiple levels of subpages in the same manner until a specific relevant discussion thread is found. Each discussion thread is then analyzed in order to isolate its atomic content components for further processing. For example, a particular relevant social media source (e.g., website) may have a web page with a thread containing 20 different posts relating to the Audi A6 automobile. In such a case, the web page would be retrieved and broken apart into 20 pieces, with each piece stored individually along with the user-profile information of the authors who posted the content.
The results of the scraping process include: the raw conversations of each social media post referred to as the raw post content data; the metadata of the raw post content; and information relating to the author of each post, as well as relationships between authors, referred to as the raw social graph data. The raw post content retrieved from the online social media sources is stored in raw content storage 133 (operation 205). This includes the actual text of the relevant social media post. The raw content metadata is also stored in raw content metadata storage 135 (operation 207). The raw content metadata includes information such as the URL of the social media website, and the length, context, and time of the post. Additionally, the raw social graph data is stored in raw social graph data storage 137 (operation 209). This data may include the social media post's author profile data such as the author's username, demographic information, number of posts to the social media website, those responding to the author's posts, and the author's contacts.
In the illustrated embodiment, the social network analysis (SNA) processing is then performed on the raw social graph data stored in raw social graph data storage 137 (operation 21 1). Here, information on each author of a social media post and on those responding to the author's post is retrieved from the raw social graph storage 137 and used to generate a social graph which includes an aggregation of social network information that can be useful in several contexts. For example, the social graph data may be analyzed to determine information about the author's social network including which authors are communicating about what topics, who is responding to which posts, what the related content is, and so on. The SNA processing is used to develop this information on networks of related authors and posts and to determine which authors are the most influential within these networks based on the social graph. The SNA processing first calculates a so-called centrality value for each author that expresses the author's degree of influence in a given social network. Authors that are connected to a large number of other authors and also connected to distinct sub-groups of authors are assumed to have higher influence than less well-connected authors. In order to calculate the centrality value, a version of Brandes' Betweenness Centrality algorithm is applied to the raw social graph for each website. The resulting raw centrality value is then modified with the activity level of the author, i.e. the number of posts written by this person, and an importance score for the website where that author is active. Within graph theory and network analysis, there are various measures of the centrality of a vertex within a graph that determine the relative importance of a vertex within the graph. Betweenness is a centrality measure of a vertex within a graph. Vertices that occur on many shortest paths between other vertices have higher betweenness than those that do not. For instance, an influential author on a large website such as MySpace® will receive a higher influence score than the author of a little known blog. In at least one embodiment, the influence score for each author is calculated by the following formula:
Influence score=bc*(ca+a/pa)*(cp+p), where
-
- bc is the raw betweenness centrality value for the author;
- a is the number of active authors on the website where the author is active;
- p is the number of posts that the author has contributed;
- ca, pa, cp are correction parameters that are fine-tuned for the purposes of a specific vertical (i.e., a specific category of interest).
The SNA processing also provides information including: the websites on which each of the social media authors have contributed; registrations in social networks; the status of influence of the authors; the author's sentiment towards a given brand, product or service; known demographic and geographic information about the authors; and trends in all of the above.
The social graph is then stored in social graph storage 141 (operation 213). An additional input into the social graph storage 141 is from user-profile scraping data accumulated from the Internet 101 using user-profile scraping module 143. At operation 215, the user profile scraping module 143 scours the Internet 101 to find any other information about the authors of the online social media conversations. Whatever information associated with the author that can be harvested from the Internet 101 is collected and stored along with the social graph in social graph storage 141 (operation 217). This completes the harvesting layer process 200 according to an exemplary embodiment.
Process 400A begins with receiving data 145 at processing module 301 from storage (operation 401). The data 145 received from storage is the output data 145 from
Sentiment rating processing is then performed using sentiment rating processing module 305 on the raw content data stored in raw content data storage 133, the raw content metadata stored in raw content metadata storage 135, and the social graph information stored in social graph storage 141 (operation 402). Sentiment rating processing includes analyzing the actual text of online social media conversations to find keywords, terms or phrases to determine if a particular post refers to the particular brand, product or service of interest. This helps to determine the sentiment about the brand, product or service. The input to sentiment rating processing module 305 includes the actual text of the social media post, lists of keywords, and so on. Industry-specific keywords are identified and a value or sentiment rating is assigned to each of these keywords. In at least certain embodiments, this processing includes natural language and sentence structure analysis to determine which parts of the text of a social media post apply to the particular brand, product or service. Once the keywords are identified, they are processed using a number of factors including how many times the keyword appears in the social media post, the closeness and linguistic context of the keyword in relation to the brand, product or service, and whether the keyword reflects a positive, negative, or neutral sentiment about the brand, product or service. This processing may also require balancing opposing keywords (e.g., both positive and negative keywords in the same post) to determine an overall sentiment rating of how positive, negative, or neutral the social media post is in relation to a brand, product or service.
Keywords are assigned with a positive and negative probability value each that express the probability that the keyword means something positive or negative in the context of the specific vertical. Since the same word can have different meanings per industry or topic, these probabilities can be specifically set per vertical. Also, some embodiments include a training or feedback loop where keywords may be re-rated over time based on experience. During the processing, terms of interest (brands, products, service names) and their synonyms are identified in the text of the social media post. In a next step, the environment (the closest n words) of this occurrence is searched for relevant sentiment keywords that might refer to the term of interest. Linguistic elements such as negations, comparatives, or enumerations are taken into account when determining the relevance of a sentiment keyword for the term of interest. Each occurrence of the term of interest is assigned with a sentiment score depending on the keywords in the environment, the linguistic modifiers present, the proximity of the keyword to the term of interest, and potentially reduced confidence due to ambiguities. Finally these atomic scores are added up for the whole post and corrected by the relevance of the post for the term of interest, i.e. the percentage of the post that actually refers to the term of interest.
This information is then combined with the social graph data from social graph storage 141 to determine a weighting factor of the social media post. That is, the sentiment rating processing of operation 402 takes into consideration the level of influence the author of the social media post has in determining the sentiment rating. A weighting factor is determined based on the influence of the author of the social media post. The resulting data from sentiment rating processing module 305 is then stored in the sentiment rating storage 309 (operation 404). Additionally, the sentiment rating data stored in sentiment rating storage 309 is aggregated over time in the sentiment aggregation queue 311 for sentiment trend processing to be discussed infra. This completes process 400A according to an exemplary embodiment and control flows to process 400B of
Process 400B begins at operation 409 where data from storage is received at processing module 302 from storage. The data received from storage includes the social graph data 149 output from social graph storage 141 of
At least certain embodiments include additional external data processing (operation 419). For example, sales data may be included in the trend processing using sales data processing module 321, traffic data may be included in the trend processing using traffic data processing module 323, and demographics data may be included in the trend processing using demographics processing 324. Sales data processing module 321 allows users to correlate the sales data with sentiment data over time. This can lead to predictions in sales volume data and pricing. Traffic data processing module 323 allows users to correlate the traffic data with sentiment data over time. Likewise, demographics processing 325 allows users to correlate demographics data with sentiment data over time. Other external data from users' database sources may also be included in the processing and correlated with sentiment data over time.
Process 400B continues with storing the results of the above processing in a database referred to herein as the vertical database (operation 421), and sending this data as output data to the user interface 705 of the presentation layer 700 for display (operation 423). Additionally, the results of the above processing are also output to the alert queue 425 for user alerts when sentiment trends change above or below a certain threshold, for example (operation 425). This allows for constant, real-time monitoring of emerging trends and consumer sentiment. This completes the vertical layer processing according to an exemplary embodiment. Control flows to
Process 600 begins with staging one or more search run definitions 503 for processing in search queue 501 (operation 601). Search run definitions contain one or more brand or product names in combination with any number of other relevant keywords that a consumer might be searching for. One or more searches of the Internet 101 corresponding to the one or more search run definitions 503 staged in search queue 501 are then performed using one or more search engine APIs 505 (operation 603). The results of these searches are fed into website and link scraping module 507. Website and link scraping is then performed (operation 605) using the website and link scraping module 507. During this operation, the top websites filtering subsystem 500 actually goes into the websites found in the one or more searches and follows the website links within each of these websites. The websites found in the searches and the links within these websites is assembled for the purpose of attempting to model search engine users' behavior by determining which websites search engine users will likely visit when they run each of the one or more searches. In at least one embodiment, this information can provide users of the SMA platform with a list of websites with a high affinity for the users' industry or products/services. This information may be useful in a variety of circumstances including allowing users to launch targeted advertising campaigns. For example, the top websites filtering subsystem 500 may run a search in Google for digital cameras and determine that a typical search engine user will only look at the first 3 web pages listed in the search results. The top websites filtering subsystem 500 will then follow the links in these 3 web pages to find more web pages and then follow the links in those web pages, and so on. The top websites filtering subsystem 500 will assemble this information and use it to build up a website and link network graph discussed below. The raw search result data resulting from website and link scraping module 507 is then stored in search result raw data storage 509 and the metadata is stored in search result raw metadata storage 511 (operation 607) to be provided to processing module 502.
Process 600 continues with performing website graph processing (operation 609). In at least one embodiment, the website graph processing includes using graph theory to analyze the website network to determine the frequency of occurrence of each website in the website network in connection with the relevant brand, product or service and to determine the relatedness of each website in the website network to that brand, product or service. Relationships between these websites and the relevant brand, product or service are analyzed to determine graph edges which indicate the strength of these relationships. First, links between websites that contain content relevant to the brand, product or service are counted. The number of links between two websites provides an indication of how strongly the two websites are interconnected.
The resulting website network graph generated by the website graph processing module 513 is then stored in website graph storage 517 (operation 611) and the data 519 from the website graph storage 517 is output to the user interface 705 of the presentation layer 700 of
Process 800 begins by receiving the data stored in the vertical database 327 of the vertical layer 300 in
Some of the advantages of the social media analytics platform are that embodiments provide: brand/product/service-level analytics including websites frequently talking about the relevant brand, product or service; social media authors frequently talking about the brand/product/service; overall volume of opinions about the brand, product or service; overall sentiment towards the brand, product or service; volume and sentiment of opinions about competing brands, products or services; competing brands, products or services most frequently mentioned in connection with the users' own brand, product or service; terms used most frequently in connection with a brand, product or service; and trends and early-warning alerts for all of the above. Embodiments also provide site-level analytics including site traffic (unique visitors and pages viewed), topic distribution of site, overall sentiment towards a given brand, product, service or technology, number of active or contributing users, relevance of the active users, relationships to other relevant sites, and trends in all of the above. Finally, embodiments provide user-level analytics (users referred to here are participants in social media sites) including: sites on which users contributed content; known identities of users, users' registrations in social networks; influence of users; users' known ownership and/or use of a given product, service or technology; users' sentiment toward a given brand, product, service or technology; users' known demographic and geographical attributes; and trends in all of the above.
In at least certain embodiments, a GUI is utilized to present the quantified and analyzed online social media content in a manner relevant to the user. The GUI may be fully customizable giving users the ability to select which charts and graphs should appear on the login page of the interface. The GUI provides an intuitive display to visualize brand, product or service sentiment over time. This display is a quantitative measure of opinion or sentiment for a brand, product, services, or its competitors and is derived from an automated aggregation of sentiment ratings on each individual post to online social media about a brand, product, services and/or those of their competitors. The GUI includes various knobs or switches to manipulate the above information in a variety of ways. Among many other things, inside the GUI users can filter information by product/service or competitor, groups of websites, data ranges, or drill down to the lowest level of granularity of the information to see the actual text of online social media posts as it appears on the originating source website. The GUI provides a visualization that allows users to give context to each social media post and gain familiarity with the posting website. The GUI is designed to be used by non-expert users without help from consultants. The GUI not only provides standard spreadsheet-style visualization such as bar and pie charts, but also highly innovative approaches including: radar screen; heatmaps; geographical visualization; 3D clustering, tag clouds, and timelines. Content may be harvested from as far back as sources make available. For example, discussion boards can have posts from many years ago. The start date on the GUI is configurable and is designed for ease-of-use allowing for a visualization of the underlying data calculations and aggregations instead of simply raw data.
The dashboard may be customized according to the users' needs. The dashboard display in
The GUI also enables users to perform keyword searches and displays a listing of the keyword search results.
Additionally, a listing of the top 10 most positive and top 10 most negative users for the brand can be displayed using the “positive/negative users” category of submenu 3301. This enables users to see who has the highest opinion of the brand and who has the lowest. As with the opinion leaders list, users can drill down into posts and brand information for these authors of online social media posts. This list can show users who are the most positive online social media authors that could be a potential source of feedback and who are the most negative online social media authors that might need extra customer service attention. Likewise, a list of blogs with posts about the category sorted by ranking can be displayed using the “influential blogs” category of submenu 3301. Here, users of the GUI can see which blogs have the highest influence with respect to the user's brands.
In addition, users may select the “top websites” category in the top-level menu. This will display a list of the websites users are most likely to reach when searching online for information about a user's brand, product or service. This feature allows users to sort top websites by importance, site name or sites without advertising. As with the opinion leader list, the centrality metric for top websites reflects importance. In this case, the centrality represents the likelihood of users reaching the site when searching for information about the users' brands, products or services. Users can then click on the URL to launch the site for reference and examination. This list can be used to confirm the best sites for messaging, advertisement and engagement, which can illuminate sites toward the top of the list (important) that have not been utilized and those toward the bottom of the list (unimportant) where valuable dollars are being expended. The list shows: the advertising vehicle on the site (if any); the number of unique users; if there is any social media on the site; and the centrality metric (importance) of the site. Users may also select the “reports” category in the top-level menu. This list shows alerts that have been triggered based on user-configuration. For example, alerts can be sent for: extremely positive or negative posts; sentiment index changes; high volume of issues mentioned in posts; posts for particular authors users wish to track; posts for specific sites; and posts containing specific keywords. In one embodiment, users can receive these alerts via e-mail or SMS notifications.
Embodiments provide methods, apparatuses, and computer-readable medium for harvesting, aggregating, and providing analytic measurements of unstructured qualitative online social media conversations including the sentiment expressed among online social media participants about a particular subject matter. The type of subject matter that can be harvested, aggregated and provided as analytic measurements is virtually limitless as any subject matter contained in social media postings is envisioned to be within the scope of this description. Likewise, the applications of the SMA platform is virtually limitless does any use of aggregated and quantified social media conversations is envisioned to be within the scope of this description. Some of the applications of the SMA platform include: providing enhanced target advertising campaigns; providing enhanced customer service at a call-center; providing enhanced market research; providing a method of improved product development; providing an enhanced method for generating opinion polls; and providing enhanced methods for National Defense intelligence to name a few.
As shown in
It will be apparent from this description that aspects of the present invention may be embodied, at least in part, in software, hardware, firmware, or in combination thereof. That is, the techniques may be carried out in a computer system or other data processing system in response to its processor, such as a microprocessor, executing sequences of instructions contained in a memory, such as ROM 3507, volatile RAM 3505, non-volatile memory 3506, cache 3504, or a remote storage device (not shown). In various embodiments, hardwired circuitry may be used in combination with software instructions to implement the present invention. Thus, the techniques are not limited to any specific combination of hardware circuitry and software or to any particular source for the instructions executed by the data processing system 3500. In addition, throughout this description, various functions and operations are described as being performed by or caused by software code to simplify description. However, those skilled in the art will recognize that what is meant by such expressions is that the functions result from execution of code by a processor, such as the microprocessor 3503.
The invention also relates to apparatus for performing the operations herein. This apparatus may be specially constructed for the required purposes, or it may comprise a general purpose computer selectively activated or reconfigured by a computer program stored in the computer. Such a computer program may be stored or transmitted in a computer-readable medium. A computer-readable medium can be used to store software and data which when executed by a data processing system, such as data processing system 3500, causes the system to perform various methods of the present invention. This executable software and data may be stored in various places including for example ROM 3507, volatile RAM 3505, non-volatile memory 3506, and/or cache 3504 as shown in
Additionally, it will be understood that the various embodiments described herein may be implemented with data processing systems which have more or fewer components than system 3500. For example, such data processing systems may be a cellular telephone or a personal digital assistant (PDA) or an entertainment system or a media player or a consumer electronic device, and et cetera, each of which can be used to implement one or more of the embodiments of the invention. The algorithms and displays presented herein are not inherently related to any particular computer system or other apparatus. Various general purpose systems may be used with programs in accordance with the teachings herein, or it may prove convenient to construct more specialized apparatuses to perform the method operations. The structure for a variety of these systems appears from the description above. In addition, the invention is not described with reference to any particular programming language. It will be appreciated that a variety of programming languages may be used to implement the teachings of the invention as described herein.
Throughout the foregoing specification, references to “one embodiment,” “an embodiment,” “an example embodiment,” and et cetera, indicate that the embodiment described may include a particular feature, structure, or characteristic, but every embodiment may not necessarily include the particular feature, structure, or characteristic. Moreover, such phrases are not necessarily referring to the same embodiment. When a particular feature, structure, or characteristic is described in connection with an embodiment, it is submitted that it is within the knowledge of one skilled in the art to bring about such a feature, structure, or characteristic in connection with other embodiments whether or not explicitly described. Various changes may be made in the structure and embodiments shown herein without departing from the principles of the invention. Further, features of the embodiments shown in various figures may be employed in combination with embodiments shown in other figures.
In the description as set forth above and claims, the terms “coupled” and “connected,” along with their derivatives, may be used. It should be understood that these terms are not intended to be synonymous with each other. Rather, in particular embodiments, “connected” is used to indicate that two or more elements are in direct physical or electrical contact with each other. “Coupled” may mean that two or more elements are in direct physical or electrical contact. However, “coupled” may also mean that two or more elements are not in direct contact with each other, but yet still co-operate or interact with each other.
Some portions of the detailed description as set forth above are presented in terms of algorithms and symbolic representations of operations on data bits within a computer memory. These algorithmic descriptions and representations are the means used by those skilled in the data processing arts to most effectively convey the substance of their work to others skilled in the art. An algorithm is here, and generally, conceived to be a self-consistent sequence of operations leading to a desired result. The operations are those requiring physical manipulations of physical quantities. Usually, though not necessarily, these quantities take the form of electrical or magnetic signals capable of being stored, transferred, combined, compared, and otherwise manipulated. It has proven convenient at times, principally for reasons of common usage, to refer to these signals as bits, values, elements, symbols, characters, terms, numbers, or the like.
It should be borne in mind, however, that all of these and similar terms are to be associated with the appropriate physical quantities and are merely convenient labels applied to these quantities. Unless specifically stated otherwise as apparent from the discussion as set forth above, it is appreciated that throughout the description, discussions utilizing terms such as “processing” or “computing” or “calculating” or “determining” or “displaying” or the like, refer to the action and processes of a computer system, or similar electronic computing device, that manipulates and transforms data represented as physical (electronic) quantities within the computer system's registers and memories into other data similarly represented as physical quantities within the computer system memories or registers or other such information storage, transmission or display devices.
Embodiments of the invention may include various operations as set forth above or fewer operations or more operations or operations in an order which is different from the order described herein. The operations may be embodied in machine-executable instructions which cause a general-purpose or special-purpose processor to perform certain operations. Alternatively, these operations may be performed by specific hardware components that contain hardwired logic for performing the operations, or by any combination of programmed computer components and custom hardware components.
Throughout the foregoing description, for the purposes of explanation, numerous specific details were set forth in order to provide a thorough understanding of the invention. It will be apparent, however, to one skilled in the art that the invention may be practiced without some of these specific details. Accordingly, the scope and spirit of the invention should be judged in terms of the claims which follow as well as the legal equivalents thereof.
Claims
1. A method comprising:
- harvesting and aggregating unstructured qualitative online social media conversations relevant to subject matter of interest in a category from one or more online social media sources;
- quantifying the aggregated online social media conversations to obtain structured analytic measurements of the online social media conversations including analytic measurements of sentiment expressed among online social media participants concerning the subject matter of interest in the category; and
- providing actionable information based on the analytic measurements of the online social media conversations.
2. The method of claim 1, wherein the actionable information is retrieved based on real-time measurements of the sentiment expressed by the online social media participants concerning the subject matter of interest and historical data representing quantitative measurements of the sentiment concerning the subject matter of interest in the past.
3. The method of claim 1, wherein the unstructured qualitative online social media conversations include messages posted to online social media websites, the messages including one or more of: Internet messages; social media postings; online dialog; blogging; interactions between customers and companies; call center logs; emails; online mail and fax communications; call center records; online purchasing information; online warranty claims; and other online traffic.
4. The method of claim 1, wherein the one or more online social media sources includes one or more of: blogs and sub-blogs; online discussion forums; social networks; wiki sites; online reviews on e-commerce sites; video websites; micro-blogging services; call centers; websites including websites of companies; and other sources of online social media conversations.
5. The method of claim 1, further comprising displaying the actionable information in a graphical user interface.
6. The method of claim 1, further comprising:
- performing sentiment rating processing on structured analytical measurements of the online social media conversations referring to the subject matter of interest to determine a sentiment rating for each of the online social media conversations; and
- assigning the sentiment rating to each of the online social media conversations.
7. The method of claim 6, wherein determining the sentiment rating includes:
- identifying terms or phrases of interest associated with the subject matter of interest in each of the online social media conversations;
- searching in a set of closest N words from the terms or phrases of interest for keywords expressing sentiment about the terms or phrases of interest;
- assigning a probability value to each of the keywords, the probability value indicating the probability that the keyword suggests something positive or negative about the terms or phrases of interest;
- assigning each occurrence of the terms or phrases of interest with a sentiment score based on the keywords in the set of closest N words from the terms or phrases of interest; and
- adding up the sentiment score assigned to each of the terms or phrases of interest in each social media conversation to obtain a sentiment rating concerning the subject matter of interest.
8. The method of claim 7, wherein the sentiment score is based on one or more of:
- how many times each occurrence of the terms or phrases of interest appears in the social media conversation;
- number of keywords expressing sentiment about the terms or phrases of interest in the set of closest words;
- whether each keyword reflects a positive, negative or neutral sentiment about the subject matter of interest; and
- relevance of the keywords expressing sentiment about the terms or phrases of interest.
9. The method of claim 8, wherein the relevance of the keywords is determined by taking into account one or more of:
- linguistic modifiers of the keywords expressing sentiment about the terms or phrases of interest including one or more of negations, comparatives, and enumerations; and
- proximity of the keywords to the terms or phrases of interest in the online social media conversation.
10. The method of claim 9, further comprising taking into account online social media author and website influence in classifying the sentiment of each online social media conversation.
11. The method of claim 1, further comprising one or more of:
- calculating how the sentiment concerning the subject matter of interest trends over time;
- calculating how the sentiment concerning the subject matter of interest varies by online source or group of sources; and
- calculating how the sentiment concerning the subject matter of interest concurrently trends over time and varies by online source or group of sources.
12. The method of claim 1, further comprising determining an overall volume of the online social media conversations referring to the subject matter of interest by adding up a number of occurrences of the subject matter of interest in online social media conversations per unit of time.
13. The method of claim 12, further comprising determining how the overall volume of online social conversations referring to the subject matter of interest trends over time.
14. The method of claim 1, further comprising determining a share of online voice acquired by the subject matter of interest with respect to other online social media subject matter.
15. The method of claim 14, wherein the other online social media subject matter includes subject matter associated with competitors in the category.
16. The method of claim 15, further comprising calculating one or more of:
- how the share of online voice acquired by the subject matter of interest trends over time; and
- how the share of online voice acquired by the subject matter of interest trends over time with respect to the subject matter of the competitors in the category.
17. The method of claim 1, further comprising performing text edge processing on the online social media conversations to determine frequency of occurrence of one or more topics in conjunction with the subject matter of interest and relatedness of the one or more topics to the subject matter of interest.
18. The method of claim 17, wherein the text edge processing comprises:
- splitting up each sentence in the online social media conversations into individual words and tuples of adjacent words;
- identifying words or tuples of interest associated with the subject matter of interest;
- identifying relationships between the words or tuples of interest and each other word and tuple in the sentence as an instance of an edge; and
- adding up each of the instances.
19. The method of claim 18, further comprising determining how the frequency of occurrence of the one or more topics in conjunction with the subject matter of interest trends over time.
20. The method of claim 14, further comprising determining an overall advocacy of the subject matter of interest in the online social media conversations for the category based on:
- the sentiment rating of the subject matter of interest;
- number of advocates of the subject matter of interest, the advocates of the subject matter of interest including online social media authors having most positive sentiment for the subject matter of interest in the category; and
- the share of online voice acquired by the subject matter of interest with respect to the subject matter associated with the competitors in the category.
21. The method of claim 1, further comprising utilizing the actionable information in conjunction with traditional research and measurements including: quantitative and qualitative market research; paid media tracking; and traditional website analytics; sales information; public relations information; advertising information; investor relations; brand management; and product development information.
22. The method of claim 1, further comprising identifying and actively engaging influential authors of online social media based on the actionable information.
23. The method of claim 1, further comprising identifying and engaging representatives of influential online social media websites.
24. The method of claim 1, wherein the actionable information includes real-time alerts providing early warnings about customer service or quality issues.
25. A method for operating an enhanced customer service call center comprising:
- receiving a customer service call at a call center from a customer concerning a product or service;
- extracting information from the customer service call; and
- retrieving actionable information stored in a database relating to the customer service call, the actionable information generated by harvesting, aggregating and quantifying unstructured qualitative online social media conversations from one or more online social media sources; and
- providing enhanced customer service to the customer based on the actionable information.
26. The method of claim 25, further comprising taking action based on the actionable information including one or more:
- recommending or performing an action based on the actionable information relevant to the customer service call; and
- providing guidance to a call-center operator on how to respond to the customer service call based on the actionable information.
27. The method of claim 26, wherein the guidance to the call-center operator includes how to deal with ongoing issues concerning the product or service.
28. The method of claim 26, wherein the guidance to the call-center operator includes identifying new issues concerning the product or service.
29. The method of claim 28, further comprising providing crisis prevention and management based on the real-time alerts.
30. The method of claim 29, wherein the real-time alerts are based on user-configurable events including one or more: abnormally positive online social media conversations about the subject matter of interest; abnormally negative online social media conversations about the subject matter of interest; changes in the sentiment expressed among online social media participants concerning the subject matter of interest above or below a pre-selected threshold; abnormally high volume of online social media posts concerning the subject matter of interest; abnormally low volume of online social media posts concerning the subject matter of interest; social media posts by certain authors; social media posts to certain websites; and social media posts containing certain keywords.
31. A method of enhancing targeted advertising campaigns comprising:
- retrieving actionable information stored in a database relating to a product or service to be advertised, the actionable information generated by harvesting, aggregating and quantifying unstructured qualitative online social media conversations from one or more online social media sources; and
- targeting advertising campaigns based on the actionable information.
32. The method of claim 31, wherein the actionable information includes one or more of:
- industry or sector corresponding to the product or service to be advertised;
- sentiment expressed by online social media participants about the product or service in the online social media conversations;
- trends in the sentiment expressed by the online social media participants about the product or service; and
- alerts concerning the product or service.
33. The method of claim 31, wherein the actionable information includes one or more of:
- most relevant websites, wherein the most relevant websites include one or more of websites most likely to be reached in online searches for information relating to the product or service and websites where high-affinity social media participants are exchanging opinions and making purchasing decisions; and
- most relevant advertisement networks for advertising the product or service.
34. The method of claim 31, wherein the actionable information provides one or more of:
- perception of the product or service among the online social media participants to be advertised;
- trend recognition of sentiment expressed by the online social media participants concerning the product or service;
- opportunity identification; and
- competitor monitoring.
35. The method of claim 31, further comprising observing results in the marketplace for the product or service based on the targeted advertising campaign.
36. A method of providing enhanced marketing research comprising:
- retrieving quantitative actionable information stored in a database relating to a product or service to be marketed, the actionable information generated by harvesting, aggregating and quantifying unstructured qualitative online social media conversations from one or more online social media sources; and
- providing enhanced marketing research based on the actionable information.
37. The method of claim 36, wherein the actionable information is made widely available inside an organization using an interface to push the actionable information to everyone inside the organization.
38. The method of claim 36, wherein the actionable information enables marketing staff to establish an overall sense of the voice of their customers and to make informed decisions at a customer level.
39. The method of claim 36, further comprising providing statistical analysis of the online social media conversations to gain insight into social behavior of potential customers to inform enhanced marketing decisions.
40. A method for enhanced product development comprising:
- retrieving quantitative actionable information stored in a database relating to one or more products, the actionable information generated by harvesting, aggregating and quantifying unstructured qualitative online social media conversations from one or more online social media sources; and
- developing new products based on the actionable information.
41. The method of claim 40, wherein the actionable information includes sentiment expressed among online social media participants about the one or more products.
42. The method of claim 41, wherein the actionable information further includes sentiment expressed among the online social media participants about one or more features of the one or more products.
43. The method of claim 40, wherein the retrieved actionable information includes information relating to one or more of competitors' products, competitors' pricing, competitors' advertising and competitors' sales strategies.
44. The method of claim 40, further comprising providing statistical analysis on the online social media conversations to gain increased knowledge of competitors based on the actionable information and develop new products in response to the actionable information.
45. A method for enhancing the gathering of opinion polls comprising:
- retrieving quantitative structured actionable information stored in a database relating to the subject matter of an opinion poll, the actionable information generated by harvesting, aggregating and quantifying unstructured qualitative online social media conversations from one or more online social media sources; and
- ascertaining opinion among online social media participants concerning the subject matter of the opinion poll based on the actionable information.
46. An method for providing enhanced national defense intelligence comprising:
- retrieving quantitative structured actionable information stored in a database related to potential violent terrorist activity, the actionable information based on harvested, aggregated and quantified unstructured qualitative online social media conversations from one or more online social media sources; and
- identifying potential violent terrorist activity in the online social media conversations based on the actionable information.
47. The method of claim 46, further comprising identifying previously unknown online social media sources used by groups to engage in violent terrorist activity based on the actionable information.
48. The method of claim 46, further comprising:
- monitoring keywords associated with violent terrorist activity in the unstructured qualitative online social media conversations;
- performing text edge processing on the keywords associated with violent terrorist activity; and
- identifying previously unknown keywords as associated with violent terrorist activity based on performing the text edge processing.
49. The method of claim 48, further comprising identifying keywords and phrases that appear with greatest frequency in the online social media conversations in conjunction with keywords and phrases identified as associated with violent terrorist activity.
50. The method of claim 46, further comprising predicting preparation, planning, and execution of violent activities based on actionable information.
51. The method of claim 46, wherein the violent terrorist activities include manufacture or distributing improvised explosive devices (IEDs).
52. An article of manufacture comprising:
- a computer-readable storage medium providing instructions which, when executed by a computer, cause the computer to perform a method of providing actionable information, the instructions comprising: instructions to harvest and aggregating unstructured qualitative online social media conversations relevant to subject matter of interest in a category from one or more online social media sources; instructions to quantify the aggregated online social media conversations to obtain structured analytic measurements of the online social media conversations including analytic measurements of sentiment expressed among online social media participants concerning the subject matter of interest in the category; and instructions to provide actionable information based on the analytic measurements of the online social media conversations.
53. The article of manufacture of claim 52, further comprising instructions to display the actionable information in a graphical user interface.
54. The article of manufacture of claim 52, further comprising:
- instructions to perform sentiment rating processing on the structured analytical measurements of the online social media conversations referring to the subject matter of interest; and
- instructions to assign a sentiment rating to each of the online social media conversations.
55. The article of manufacture of claim 54, further comprising instructions to determine the sentiment rating including:
- instructions to identify terms or phrases of interest associated with the subject matter of interest in each of the online social media conversations;
- instructions to search in a set of closest N words from the terms or phrases of interest for keywords expressing sentiment about the terms or phrases of interest;
- instructions to assign a probability value to each of the keywords, the probability value indicating the probability that the keyword suggests something positive or negative about the terms or phrases of interest;
- instructions to assign each occurrence of the terms or phrases of interest with a sentiment score based on the keywords in the set of closest N words from the terms or phrases of interest; and
- instructions to add up the sentiment score assigned to each of the terms or phrases of interest in each social media conversation to obtain a sentiment rating concerning the subject matter of interest.
56. The article of manufacture of claim 52, further comprising one or more of:
- instructions to calculate how the sentiment concerning the subject matter of interest trends over time;
- instructions to calculate how the sentiment concerning the subject matter of interest varies by online source or group of sources; and
- instructions to calculate how the sentiment concerning the subject matter of interest concurrently trends over time and varies by online source or group of sources.
57. The article of manufacture of claim 52, further comprising instructions to determine an overall volume of the online social media conversations referring to the subject matter of interest by adding up a number of occurrences of the subject matter of interest in online social media conversations per unit of time.
58. The article of manufacture of claim 57, further comprising instructions to determine how the overall volume of online social conversations referring to the subject matter of interest trends over time.
59. The article of manufacture of claim 52, further comprising instructions to determine a share of online voice acquired by the subject matter of interest with respect to other online social media subject matter.
60. The article of manufacture of claim 59, wherein the other online social media subject matter includes subject matter associated with competitors in the category.
61. The article of manufacture of claim 60, further comprising instructions to calculate one or more of:
- how the share of online voice acquired by the subject matter of interest trends over time; and
- how the share of online voice acquired by the subject matter of interest trends over time with respect to the subject matter of the competitors in the category.
62. The article of manufacture of claim 52, further comprising instructions to perform text edge processing on the online social media conversations to determine frequency of occurrence of one or more topics in conjunction with the subject matter of interest and relatedness of the one or more topics to the subject matter of interest.
63. An article of manufacture comprising:
- a computer-readable storage medium providing instructions which, when executed by a computer, cause the computer to perform for operating an enhanced customer service call center, the instructions comprising: instructions to receive a customer service call at a call center from a customer concerning a product or service; instructions to extract information from the customer service call; instructions to retrieve actionable information stored in a database relating to the customer service call, the actionable information generated by harvesting, aggregating and quantifying unstructured qualitative online social media conversations from one or more online social media sources; and instructions to provide enhanced customer service to the customer based on the actionable information.
64. The article of manufacture of claim 63, further comprising instructions to take action based on the actionable information including one or more:
- instructions to recommend or perform an action based on the actionable information relevant to the customer service call; and
- instructions to provide guidance to a call-center operator on how to respond to the customer service call based on the actionable information.
65. The article of manufacture of claim 64, wherein the guidance to the call-center operator includes how to deal with ongoing issues concerning the product or service and how to identify new issues concerning the product or service.
66. The article of manufacture of claim 63, further comprising instructions to identify and engage representatives of influential online social media websites.
67. The article of manufacture of claim 63, wherein the actionable information includes real-time alerts providing early warnings about customer service or quality issues.
68. The article of manufacture of claim 67, further comprising instructions to provide crisis prevention and management based on the real-time alerts.
69. An article of manufacture comprising:
- a computer-readable storage medium providing instructions which, when executed by a computer, cause the computer to perform a method of enhancing targeted advertising campaigns, the instructions comprising: instructions to retrieve actionable information stored in a database relating to a product or service to be advertised, the actionable information generated by harvesting, aggregating and quantifying unstructured qualitative online social media conversations from one or more online social media sources; and instructions to target advertising campaigns based on the actionable information.
70. The article of manufacture of claim 69, wherein the actionable information includes one or more:
- industry or sector corresponding to the product or service to be advertised;
- sentiment expressed by online social media participants about the product or service in the online social media conversations;
- trends in the sentiment expressed by the online social media participants about the product or service; and
- alerts concerning the product or service.
71. The article of manufacture of claim 69, wherein the actionable information includes one or more of:
- most relevant websites, wherein the most relevant websites include one or more of websites most likely to be reached in online searches for information relating to the product or service and websites where high-affinity social media participants are exchanging opinions and making purchasing decisions; and
- most relevant advertisement networks for advertising the product or service.
72. The article of manufacture of claim 69, wherein the actionable information provides one or more of:
- perception of the product or service among the online social media participants to be advertised;
- trend recognition of sentiment expressed by the online social media participants concerning the product or service;
- opportunity identification; and
- competitor or monitoring.
73. The article of manufacture of claim 69, further comprising instructions to observe results in the marketplace for the product or service based on the targeted advertising campaign.
74. An article of manufacture comprising:
- a computer-readable storage medium providing instructions which, when executed by a computer, cause the computer to perform a method of enhancing marketing research, the instructions comprising: instructions to retrieve quantitative actionable information stored in a database relating to a product or service to be marketed, the actionable information generated by harvesting, aggregating and quantifying unstructured qualitative online social media conversations from one or more online social media sources; and instruction to provide enhanced marketing research based on the actionable information.
75. The article of manufacture of claim 74, wherein the actionable information is made widely available inside an organization using an interface to push the actionable information to everyone inside the organization.
76. The article of manufacture of claim 74, wherein the actionable information enables marketing staff to establish an overall sense of the voice of their customers and to make informed decisions at a customer level.
77. The article of manufacture of claim 74, further comprising instructions to provide statistical analysis of the online social media conversations to gain insight into social behavior of potential customers to inform enhanced marketing decisions.
78. An article of manufacture comprising:
- a computer-readable storage medium providing instructions which, when executed by a computer, cause the computer to perform a method of improved product development, the instructions comprising: instructions to retrieve quantitative actionable stored in a database information relating to one or more products, the actionable information generated by harvesting, aggregating and quantifying unstructured qualitative online social media conversations from one or more online social media sources; and instructions to develop new products based on the actionable information.
79. The article of manufacture of claim 78, wherein the actionable information includes sentiment expressed among online social media participants about the one or more products.
80. The article of manufacture of claim 79, wherein the actionable information further includes sentiment expressed among the online social media participants about one or more features of the one or more products of the user of the social media analytics platform.
81. The article of manufacture of claim 79, wherein the retrieved actionable information includes information relating to one or more of competitors' products, competitors' pricing, competitors' advertising and competitors' sales strategies.
82. The article of manufacture of claim 79, further comprising instructions to provide statistical analysis on the online social media conversations to gain increased knowledge of competitors based on the actionable information and develop new products in response to the actionable information.
83. An article of manufacture comprising:
- a computer-readable storage medium providing instructions which, when executed by a computer, cause the computer to perform a method for enhanced opinion polling, the instructions comprising: instructions to retrieve quantitative structured actionable information stored in a database relating to the subject matter of an opinion poll, the actionable information generated by harvesting, aggregating and quantifying unstructured qualitative online social media conversations from one or more online social media sources; and instructions to ascertain opinion among online social media participants concerning the subject matter of the opinion poll based on the actionable information.
84. An article of manufacture comprising:
- a computer-readable storage medium providing instructions which, when executed by a computer, cause the computer to perform a method for providing enhanced national defense intelligence, the instructions comprising: instructions to retrieve quantitative structured actionable information stored in a database related to potential violent terrorist activity, the actionable information based on harvested, aggregated and quantified unstructured qualitative online social media conversations from one or more online social media sources; and instructions to identify potential violent terrorist activity in the online social media conversations based on the actionable information.
85. The article of manufacture of claim 84, further comprising instructions to identify previously unknown online social media sources used by groups to engage in violent terrorist activity based on the actionable information.
86. The article of manufacture of claim 84, further comprising:
- instructions to monitor keywords associated with violent terrorist activity in the unstructured qualitative online social media conversations;
- instructions to perform text edge processing on the keywords associated with violent terrorist activity; and
- instructions to identify previously unknown keywords as associated with violent terrorist activity based on performing the text edge processing.
87. The article of manufacture of claim 86, further comprising instructions to identify keywords that appear with greatest frequency in conjunction with keywords and phrases in the online social media conversations identified as associated with violent terrorist activity.
88. The article of manufacture of claim 84, further comprising instructions to predict preparation, planning, and execution of violent activities based on actionable information.
89. The article of manufacture of claim 84, wherein the violent activities include manufacture or distributing improvised explosive devices (IEDs).
90. An apparatus comprising:
- a harvesting module configured to harvest online social media conversations relevant to subject matter of interest in a category from one or more online social media sources; and
- a vertical module configured to: aggregate the harvested online social media conversations; quantify the aggregated online social media conversations to obtain structured analytic measurements of the online social media conversations including analytic measurements of sentiment expressed among online social media participants concerning the subject matter of interest in the category; and provide actionable information based on the analytic measurements of the online social media conversations.
91. The apparatus of claim 90, wherein the vertical module comprises a sentiment rating processing module configured to rate the sentiment expressed among online social media participants concerning subject matter of interest.
92. The apparatus of claim 90, wherein the vertical module comprises a text edge processing module configured to determine:
- frequency of occurrence of one or more topics in conjunction with subject matter of interest; and
- relatedness of the one or more topics to the subject matter of interest.
93. The apparatus of claim 92, wherein the vertical module further includes a text trend processing module configured to quantify how the frequency of occurrence of the one or more topics in conjunction with the subject matter of interest trends over time.
94. The apparatus of claim 90, wherein the vertical module further includes a volume trend processing module to perform one or more of:
- calculate an overall volume of harvested online social media conversations referring to the subject matter of interest; and
- calculate how the overall volume of harvested online social media conversations referring to the subject matter of interest trends over time.
95. The apparatus of claim 90, wherein the vertical module further includes a sentiment aggregation processing module configured to perform one or more of:
- calculate how the sentiment among online social media participants concerning the subject matter of interest trends over time; and
- calculate how the sentiment concerning the subject matter of interest varies by online source or group of sources.
Type: Application
Filed: Jan 13, 2009
Publication Date: May 13, 2010
Applicant: Buzzient, Inc. (Cambridge, MA)
Inventor: Andreas Goeldi (Cambridge, MA)
Application Number: 12/352,827
International Classification: H04M 3/00 (20060101); G06F 17/30 (20060101); G06Q 30/00 (20060101); G06Q 99/00 (20060101); G06Q 10/00 (20060101); G06F 17/27 (20060101);