Abstract: Techniques and systems for assisting an author in creating content for social media (e.g., blog posts, microblogs, tweets, etc.) are disclosed, wherein hints are provided to the author as a function of social media stored in a social media knowledge store. Social media is collected and stored in a social media knowledge store according to some criteria. Upon the happening of some predetermined event, for example, relevant information is retrieved from the social media knowledge store. The relevancy of information may be a function of editing context (provided by the author) and/or social media behavior, for example. The relevant information may be translated into hints that provide an author with suggestions and/or corrections, for example. This information is provided to the author through a social media environment (e.g., an authoring tool) that may be also be capable of receiving input from the author and outputting editing context.

Abstract: A method and system for retrieving data from a webpage is described herein. A scheduler organizes, or rather orders, a group of webpage identifiers according to some predetermined criteria. Based upon this ordering, a fetcher may be configured to fetch data from webpages identified by the identifiers. To promote efficiency and reduce the latency between when a webpage is updated and when the fetcher retrieves data from the webpage, the scheduler may be configured to reorder the identifiers in such a manner that it causes an identifier that was less relevant, and would not have been sent to the fetcher, to become more relevant. In this way, the method and system may be particularly useful for retrieving data related to webpages that are updated frequently, such as social media webpages, for example.

Abstract: An overwhelming number of articles are available everyday via the internet. Unfortunately, it is impossible to peruse more than a handful, and it is difficult to ascertain an article's social context. The techniques disclosed herein address this problem by harnessing implicit and explicit contextual information from social media. By extracting text surrounding a hyperlink to an article in a post and assessing the article as a function of content surrounding the hyperlink, an article's social context is determined and presented. Additionally, articles that are sufficiently similar in content may be grouped to establish a many-to-one relationship between posts and an article, creating a more accurate assessment.

Abstract: The present application presents methods for performing topical sentiment analysis on electronically stored communications employing fusion of polarity and topicality. The present application also provides methods for utilizing shallow NLP techniques to determine the polarity of an expression. The present application also provides a method for tuning a domain-specific polarity lexicon for use in the polarity determination. The present application also provides methods for computing a numeric metric of the aggregate opinion about some topic expressed in a set of expressions.

Abstract: Certain types of entities may be extracted from a document. In one example, the entities to be recognized are cultural entities, such as the names of movies, video games, books, etc. For each such entity, a concept graph may be built that shows the relationship between the entity itself and other entities, such as the relationship between a movie and the actor(s) who act in the movie. When a candidate entity name is detected in the document, the concept graph may be used to look for other entities that appear in the context of the candidate entity. The presence of related entities in the context of the candidate may be used to disambiguate the meaning of the candidate. For example, a common word like “up” might be recognized as the name of a movie if the names of actors or characters in that movie appear near the word “up”.

Abstract: The present application presents methods for performing topical sentiment analysis on electronically stored communications employing fusion of polarity and topicality. The present application also provides methods for utilizing shallow NLP techniques to determine the polarity of an expression. The present application also provides a method for tuning a domain-specific polarity lexicon for use in the polarity determination. The present application also provides methods for computing a numeric metric of the aggregate opinion about some topic expressed in a set of expressions.

Abstract: The present application presents methods for performing topical sentiment analysis on electronically stored communications employing fusion of polarity and topicality. The present application also provides methods for utilizing shallow NLP techniques to determine the polarity of an expression. The present application also provides a method for tuning a domain-specific polarity lexicon for use in the polarity determination. The present application also provides methods for computing a numeric metric of the aggregate opinion about some topic expressed in a set of expressions.

Abstract: A method and system for retrieving data from a webpage is described herein. A scheduler organizes, or rather orders, a group of webpage identifiers according to some predetermined criteria. Based upon this ordering, a fetcher may be configured to fetch data from webpages identified by the identifiers. To promote efficiency and reduce the latency between when a webpage is updated and when the fetcher retrieves data from the webpage, the scheduler may be configured to reorder the identifiers in such a manner that it causes an identifier that was less relevant, and would not have been sent to the fetcher, to become more relevant. In this way, the method and system may be particularly useful for retrieving data related to webpages that are updated frequently, such as social media webpages, for example.

Abstract: An arrangement for resolving ambiguity among named entities in web based text documents is provided in which multiple documents are utilized that are of different genres and will thus typically use different degrees of precision when referring to named entities. When an ambiguous named entity is located in a document, any links contained in that document are followed to other documents. If a linked document includes a named entity that is fully specified (i.e., includes both a first and last name), then this information can be used to resolve the ambiguity of the named entity in the original document.

Abstract: Techniques and systems for assisting an author in creating content for social media (e.g., blog posts, microblogs, tweets, etc.) are disclosed, wherein hints are provided to the author as a function of social media stored in a social media knowledge store. Social media is collected and stored in a social media knowledge store according to some criteria. Upon the happening of some predetermined event, for example, relevant information is retrieved from the social media knowledge store. The relevancy of information may be a function of editing context (provided by the author) and/or social media behavior, for example. The relevant information may be translated into hints that provide an author with suggestions and/or corrections, for example. This information is provided to the author through a social media environment (e.g., an authoring tool) that may be also be capable of receiving input from the author and outputting editing context.

Abstract: An overwhelming number of articles are available everyday via the internet. Unfortunately, it is impossible to peruse more than a handful, and it is difficult to ascertain an article's social context. The techniques disclosed herein address this problem by harnessing implicit and explicit contextual information from social media. By extracting text surrounding a hyperlink to an article in a post and assessing the article as a function of content surrounding the hyperlink, an article's social context is determined and presented. Additionally, articles that are sufficiently similar in content may be grouped to establish a many-to-one relationship between posts and an article, creating a more accurate assessment.

Abstract: The present application presents methods for performing topical sentiment analysis on electronically stored communications employing fusion of polarity and topicality. The present application also provides methods for utilizing shallow NLP techniques to determine the polarity of an expression. The present application also provides a method for tuning a domain-specific polarity lexicon for use in the polarity determination. The present application also provides methods for computing a numeric metric of the aggregate opinion about some topic expressed in a set of expressions.

Abstract: The present application presents methods for performing topical sentiment analysis on electronically stored communications employing fusion of polarity and topicality. The present application also provides methods for utilizing shallow NLP techniques to determine the polarity of an expression. The present application also provides a method for tuning a domain-specific polarity lexicon for use in the polarity determination. The present application also provides methods for computing a numeric metric of the aggregate opinion about some topic expressed in a set of expressions.

Abstract: A technique for extracting a meaningful text block from a document where a table, an itemized list, a multiple column, etc., are arbitrarily laid out. A document is input which is laid out using blanks or the like, then a symbol is acquired which is associated with a spatial coordinate of the document. Consecutive characters of the same type are extracted from the symbol to generate a token and a space. A stream is generated from consecutive spaces in the column direction, while a text block is generated from streams and tokens. A link is generated between the text blocks to form a document graph. Validity of a connection (link) between the text blocks in the document graph is evaluated using a language model, then the text blocks are merged if the connection is valid.

Abstract: A technique for extracting a meaningful text block from a document where a table, an itemized list, a multiple column, etc., are arbitrarily laid out. A document is input which is laid out using blanks or the like, then a symbol is acquired which is associated with a spatial coordinate of the document. Consecutive characters of the same type are extracted from the symbol to generate a token and a space. A stream is generated from consecutive spaces in the column direction, while a text block is generated from streams and tokens. A link is generated between the text blocks to form a document graph. Validity of a connection (link) between the text blocks in the document graph is evaluated using a language model, then the text blocks are merged if the connection is valid.