Abstract: A specific target-oriented social media tweet sentiment analysis method includes: preprocessing social media tweet data to obtain a target text and a specific target; passing the target text and the specific target through an embedding layer to obtain target text word vectors and obtain a specific target word vector, respectively; passing the target text word vectors through a self-attention structure to obtain a self-attention result; combining the self-attention result with the specific target word vector and passing through a cross-attention structure to obtain cross-attention results; concatenating the cross-attention results to obtain an attention representation matrix; and passing the attention representation matrix through a pooling layer, a fully connected layer and a softmax layer to obtain a sentiment tendency of the specific target.

Abstract: The disclosed embodiments include methods, systems, and articles of manufacture for enabling beta testing of new features within a native application. In one embodiment, a native application executed by a client device may include executable instructions that are activated and executed only upon indication of a user belonging to a beta test group. The client device may receive a signal from a service or content provider that includes test group information indicating whether a user is a member of a test group. The client device may process the received signal to determine whether the user is a member of a test group and, if so, activates and executes certain instructions received as part of the native application that define a user interface enabling access to additional functionality unavailable to a user determined not to be a member of a test group.

Abstract: A sentiment analysis computing system includes a storage medium and a processing system. Sentiment input is received from audience members viewing a streamed/webcasted event. The received input is stored to the storage medium. A time slice of the webcasted event is determined and sentiment inputs that are within that time slice are obtained. A sentiment value is calculated for the determined time slice based on aggregated sentiment values. The calculated sentiment value for the time slice is then output by the sentiment analysis computing system.

Abstract: The system receives a message having a sender and a recipient. The system identifies entities associated with the message and associated with any content that is associated with the message. The system determines whether to, and how to, modify the message based on relationship information among the sender, the recipient, and any entities identified in the message or components of the message. A relationship between a sender and recipient may be determined using, for example, a database of relationship information. The system modifies, for example, text, images, or video of the message to generate the personalized message. The personalized message include the original message along with context information to help indicate the relevance of the message to the recipient. The context information can include text, images, video, or other information. To illustrate, the context information can include keywords or identifiers that indicate entities associated with the message.

Abstract: A computer-implemented framework and/or system for cyberbullying detection is disclosed. The system includes two main components: (1) A representation learning network that encodes the social media session by exploiting multi-modal features, e.g., text, network, and time; and (2) a multi-task learning network that simultaneously fits the comment inter-arrival times and estimates the bullying likelihood based on a Gaussian Mixture Model. The system jointly optimizes the parameters of both components to overcome the shortcomings of decoupled training. The system includes an unsupervised cyberbullying detection model that not only experimentally outperforms the state-of-the-art unsupervised models, but also achieves competitive performance compared to supervised models.

Abstract: This document presents devices, systems, and their methods of use for content generation, engagement, and distribution by which a user can interact with collected content in a variety of different manners. Generally, a content engagement platform is provided, where the platform may be implemented on one or more computing devices, such as one or more of: a remote server, a desktop computer, a tablet computer, a handheld mobile computing device, for instance, a mobile phone or personal digital assistant, a smart accessory, such as a watch or eyeglasses, and the like. The platform allows a user to annotate and distribute video content.

Abstract: A system for viewing shopping information on a social networking platform is disclosed. At the social networking platform, the system receives a request from a user device corresponding to a first user of the social networking platform to view a list of a second user of the social networking platform. The list may include items offered for transaction on a network-based commerce server. In response to receiving the request from the user device, the system forwards the request to the network-based commerce server, and then receives updated information for at least one item on the list from the network-based corner server. Then, the system communicates the updated information received from the network-based commerce server to the user device.

Abstract: Systems, apparatus, and methods for media playback based on cue points. Various embodiments of the present disclosure are directed to instructional media components (e.g., video, audio, and/or text) that focus the user's attention on details of proper form. The cue point navigation system enables the user to navigate the instructional media according to specific movement cues. Notably, the UI minimizes navigational complexity, while simultaneously maximizing user comprehension. As described in greater detail herein, hybrid media playback advantageously provides the user with different ways to absorb the instructional information.

Abstract: A processing system uses a set of rules that identify a set of keywords and stores a set of creative images associated with the keywords. The processing system identifies metrics for the social media that includes the keywords and displays the creative images associated with the keywords with the largest social media metrics. The set of rules may include promotions to display with the creative content and filters that determine what social media to use to generate the metrics. No manual curation of content is necessary. The processing system saves time and effort as well as taps into real time consumer trends.

Abstract: A determination device includes a memory, and processing circuitry coupled to the memory and configured to accept input of a plurality of sequences provided as candidates for a solution to one given input, and determine, for two sequences of the plurality of sequences, a sequence that has a higher accuracy than the other sequence of the two sequences, using a model expressed as a neural network.

Abstract: Systems and methods are presented for generating recommendations using multi-level social network analysis of user behavior. In some embodiments, the system receives a set of user interactions, from a plurality of users, performed on a set of data objects; generates a set of associations between the set of data objects; and identifies a set of data object clusters indicative of the set of associations. The system generates an organization of the set of data objects based on the set of associations and the set of data object clusters and causes presentation of a plurality of data objects of the set of data objects on a user interface of a user device based on the organization.

Abstract: Devices and techniques are generally described for ranking of search results. In some examples, a query may be received. A first ranked list of content items may be determined for the query ranked based on a first optimization objective. A second ranked list of the content items may be determined for the query ranked based on a second optimization objective. A first rank product may be determined for a first content item based at least in part on multiplication of a rank of the first content item in the first ranked list with a rank of the first content item in the second ranked list. A third ranked list of the content items may be determined based at least in part on the first rank product. At least a portion of the third ranked list of the content items may be displayed on a display.

Abstract: A mechanism to automate the aggregation of independent videos for integration includes a video networking platform comprising one or more user accounts that upload one or more recorded videos having metadata to a video networking platform. A playing module plays the one or more displayed recorded videos and synchronizes the one or more recorded videos based at least in part on the metadata of the recorded video.

Abstract: A control device includes: a communication unit that receives input data from a terminal device of a first member who is a member of a first family staying in a vehicle, the input data indicating a family composition and a family stress for the first family; and a control unit that searches a database in which data indicating the family composition and the family stress for each of a plurality of families staying in individual vehicles is registered, using the input data received by the communication unit as a search key, selects a second family from the families based on a search result obtained, and causes the communication unit to transmit notification data that notifies the first member of information for establishing a relationship with a second member who is a member of the second family selected.

Abstract: In certain embodiments, one or more images of an object may be received from a device associated with a first account on a communications network. Features of the object may be extracted based on the one or more images, and one or more content items related to the object may be determined based on the features. A hashtag associated with at least one of the features may be determined. A second account connected to the first account may be selected where the second account previously performed a search for the hashtag on the communications network, and at least one of the one or more content items may be provided to the second account.

Abstract: A method and system assists experts associated with an electronic bookkeeping system to increase a rate at which users select to receive the services of the expert. The method and system retain information regarding the selection rates of a plurality of experts, and the profiles of the plurality of experts. The method and system trains an analysis model with a machine learnings process to learn how the attributes in the profiles relate to the selection rates. The method and system then utilizes the analysis model to predict changes to the profile that an expert can make to increase the selection rate of the expert. The method and system outputs recommendation data to the expert recommending one or more changes in the expert's profile that will likely result in an increase in the expert's selection rate.

Abstract: In non-limiting examples of the present disclosure, systems, methods and devices for initiating and managing electronic focus sessions are provided. A focus session window may be displayed. The focus session window may comprise a timer pane comprising a focus session duration input element; a task pane comprising an identity of at least one task object created by a task management application; a music pane comprising an identity of at least one music playlist; and/or a daily progress pane that includes a goal display element indicating a duration of time spent in focus sessions for a current day. An indication to initiate a focus session may be received. The initiating may comprise causing a timer for the duration of time to be initiated and displayed in the timer pane and causing one of the music playlists to be automatically played.

Abstract: Embodiments of the present disclosure provide a method, apparatus, and computer-readable medium for leveraging connections. One embodiment is a method that includes determining, by a processor, a plurality of subset lists of leads from a list of leads, and creating, by the processor, a message for each one of the plurality of subset lists of leads to one of a plurality of collaborators. The method further includes transmitting, by the processor, each message with one of the plurality of subset lists of leads to each of the plurality of collaborators from a user.

Abstract: In general, the subject matter described in the specification can be embodied in methods, systems and program products for a verified participant database system that verifies information on potential participants for surveys and promotions that require numerous participants with certain characteristics. Among other features, the verified participant database system aggregates and preferably verifies information, for example, the demographic and purchasing information, of potential participants by receiving permission to obtain information from third-party sources.

Abstract: An apparatus includes an interface and a processor. The interface sends and receives data over a network. The processor uses the interface to transmit a first series of profiles to a first user that includes recommended profiles for a second user. The processor uses the interface to receive a selection from the first user of a profile corresponding to a third user. The processor uses the interface to transmit a second series of profiles to the third user that includes recommended profiles for the third user. The processor uses the interface to receive a selection from the third user of a profile corresponding to the second user. In response to receiving the selection from the first user of the profile corresponding to the third user and the selection from the third user of the profile corresponding to the second user, the processor enables communication between the second and third users.

Abstract: Systems and methods deliver advertisements to electronic billboards, additionally deliver social media content relevant to the advertisements, control content of the electronic billboards, including through social media interactions, and deliver interactive applications to the electronic billboards and control the interactive applications. An advertisement is delivered to an electronic billboard for display, and social media content relevant to the advertisement is also delivered to the electronic billboard for display in real time. The social media content is used to update the display of the electronic billboard in temporal proximity to a time of posting of social media content. Content and applications are received at the electronic billboard by push, and may be removed from storage of electronic billboard after display to make storage room available for additional interactive applications and to ensure that updated content is always displayed.

Abstract: A personalized comment recommendation method based on a link prediction model of a graph bidirectional aggregation network. In a user-comment bipartite graph, comment features are aggregated into a user feature. A social network is used to fuse a neighbor feature of a user to obtain an embedding representation of the user. The embedding representation of the user is aggregated into a comment after an original feature of the user is removed, and the embedding representation of the user is adjusted based on a difference before and after comment aggregation. On this basis, a forwarding network is used to calculate a score of an edge based on an inner product of user node features at both ends of the edge, and finally make a recommendation based on the score. Furthermore, a recommendation system converts a comment recommendation task into a link prediction task between users in a small range.

Abstract: Examples can include a system for video chat cycles within a social media application. An organizer platform can be used to design a schedule for the video chat cycles. This can include scheduled organizer content before, after, and between video chats. The organizer content can include graphics, video, and even live streams by the organizer.

Abstract: Systems, methods, and computer program products for executing a sequence of tasks are provided. An analytics engine receives a request to execute a group of tasks, where tasks execute in different programming languages. A sequence for executing the tasks in the group of tasks is determined using the input and output parameters of the tasks. The tasks are executed according to a determined sequence. To execute each task, the analytics engine instantiates a process that corresponds to programming language associated with the tasks. The process executes the task. Once all tasks complete execution, an output of the last task is a result of the group of tasks.

Abstract: Methods, systems, and media for presenting recommended content based on social cues are provided. In accordance with some embodiments, a method for presenting recommended content is provided comprising: receiving a query associated with a user; generating a list of relevant media content items based on the query; selecting items for presentation to the user based on social relevance scores based on social connections of the user that have consumed a relevant item and contextual relevance scores for each item; causing the selected items to be presented to the user; and indicating that a particular item was consumed by a particular social connection.

Abstract: Systems, devices, and methods for automating network account transfers based on predicted inactivity are disclosed.

Abstract: An apparatus, method and computer program product may be provided for updating a graph-based knowledge representation data structure using one or more conversation segments. Updating a graph-based knowledge representation data structure may include receiving a conversation segment. The conversation segment may comprise one or more group-based communication messages and one or more sending user identifiers of the one or more group-based communication messages. Updating a graph-based knowledge representation data structure may further include identifying the one or more sending user identifiers of each group-based communication message of the conversation segment. Updating a graph-based knowledge representation data structure may further include determining one or more user identifiers of the sending user identifiers that satisfy conversation participation criteria.

Abstract: A system and apparatus for rating accessibility of a number of locations for user and/or members with specific accessibility needs. The user and/or member interacts with a database through his or her communication device or through a website to access locations in a geographic zone that provide accommodations for people with specific accessibility needs in a variety of accessibility categories. The system provides detailed accessibility features within each accessibility category and rates the locations according to the accessibility categories. The member can also input new locations, rate locations already contained in the database, or provide other feedback regarding compliance with legal accessibility guidelines and/or other accessibility standards within the United States and abroad. The system updates the ratings of the accessibility categories and the accessibility features based on input from members.

Abstract: One or more computing devices, systems, and/or methods are provided. Activity of a plurality of devices may be analyzed to identify network traffic. A network profile associated with the plurality of devices may be generated based upon the network traffic. The network profile may be indicative of one or more sets of transmission metrics associated with a first device of the plurality of devices. The network profile may be indicative of one or more sets of reception metrics associated with the first device. Content may be generated based upon the network profile. The content may be transmitted to a device based upon the network profile.

Abstract: A system and method of identifying suspicious item-related features are disclosed. In some embodiments, a new item listing is received. The item listing may correspond to a request to list an item for sale on an e-commerce website. Item-related data for the item listing may be extracted. The item-related data can be used by a model to classify the new item listing. The model may be trained on data comprising identifications of which item listings in the sample of item listings are suspicious and identifications of which item listings in the sample of item listings are not suspicious may be received.

Abstract: In some embodiments, a network node for securing physical assets may be provided. The network node may include a processor and a memory storing instructions. The network may be configured to: receive, from a first entity, a cryptographic data structure configured to identify a physical item stored in a secured location; in response to receiving the cryptographic data structure, generate and transmit to the first entity a plurality of fungible cryptographic items; secure the cryptographic data structure on a public data structure, such that the cryptographic data structure cannot be released unless the plurality of fungible cryptographic items are received; receive, from a second entity, the plurality of fungible cryptographic items; and in response to receiving the plurality of fungible cryptographic items, transmit to the second entity the cryptographic data structure.

Abstract: Systems, methods, and computer program products for adaptively splitting electronic chats are provided. An e-discovery system comprises a computer processor and a non-transitory, computer-readable medium embodying thereon a set of computer instructions executable by the computer processor. The set of computer instructions includes instructions for: sending a chat query to a remote electronic chat service; receiving an electronic chat responsive to the chat query, the electronic chat embodying a set of electronic chat messages; adaptively splitting the set of electronic chat messages into a set of conversations, each conversation in the set of conversations comprising a subset of electronic chat messages from the set of electronic chat messages; and storing each conversation from the set of conversations as a separate document.

Abstract: Provided is a plan coordination apparatus that swiftly coordinates plans between business operators regardless of presence or absence of product order placement/receipt-relation. The plan coordination apparatus includes a value chain management unit and a scheduling unit. The value chain management unit prepares value chain data, recalculates reliability of order placement/receipt-relation between the business operators each time a new track record of product order placement/receipt-relation is collected, updates the reliability, and assigns the reliability to the edge. The scheduling unit accepts a plan alteration request from one of the business operators to be managed, refers to automatically adjustable volumes of the product data, the value chain data, and the plan data, judges whether a related business operator can alter the plan, identifies an alternative business operator, gives a notification of the alteration of the plan to the business operator, and alters the plan data.

Abstract: Cognitive and heuristics-based emergent financial management is provided. A method includes obtaining data related to an individual, an organization, a process, or combinations thereof. The data is obtained from internal sources, external sources, or combinations thereof. The method also includes creating data sets from the data based on determined classifications of the data. Further, the method includes establishing relationships between the data sets and determining a conclusion based on the relationships. The conclusion is based on a hypothesis that has undergone a test process.

Abstract: Systems and methods which utilize one or more social networking systems when creating, funding, and/or notifying a party of a transaction are provided. In accordance with one aspect, a money transfer transaction may be staged by a user whereupon a link corresponding to the staged transaction may be posted to one or more social networking services in order to allow for multiple users to access and fund the staged transaction. Additionally, in some aspects a user of a social networking service may generate a comment or post which then automatically triggers the staging of a money transfer transaction. Moreover, social networking services may be utilized to provide various notifications regarding money transfer transactions.

Abstract: Systems and methods for computer-implemented evaluation of a performance are provided. In a first aspect, a computer-implemented method of evaluating an interaction generates a first temporal record of first behavior features exhibited by a first entity during an interaction between a first entity and a second entity. A second temporal record is generated including second behavior features exhibited by a second entity during an interaction with a first entity. A determination is made that a first feature of a first temporal record is associated with a second feature of a second temporal record. The length of time that passes between the first feature and second feature is evaluated, and a determination is made that the length of time satisfies a temporal condition. A co-occurrence record associated with a first feature and a second feature is generated and included in a co-occurrence record data-structure.

Abstract: Provided is a system and method for generating job posting content through machine learning. In one example, the method may include storing text content of previous postings, receiving target attributes of a candidate that is a subject of a new posting, identifying, via a machine learning model, a subset of previous postings from among the previous postings which are most closely related to the new posting based on the target attributes of the candidate with respect to content of the previous postings, and detecting text objects from the identified subset of previous postings and outputting a display of the detected text objects.

Abstract: Embedding applications, or parts thereof, into other applications, or parts thereof, is described. In an example, an engagement with a first application, or a part thereof, can be detected, which can trigger a second application, or a part thereof, to be initialized in response to the engagement. In at least one example, the first application, or a part thereof, can provisionally transfer to the second application, or a part thereof. Based at least in part on detecting a user interaction with the second application, or a part thereof, a portion of the user interaction can be embedded in the first application, or a part thereof, and the embedded portion of the user interaction can be presented via a user interface associated with the first application, or part thereof, via a user computing device.

Abstract: An online system presents a content item to users and receives selections of reaction icons from the users. The online system generates a background animation with the selected reaction icons and a foreground animation to be layered on top of the background animation. The online system sends the background and foreground animations to a client device to be cached. Further, the online system presents the content item to a viewing user associated with the client device and receives a selection of a reaction icon from the viewing user. The online system selects a subset of the users based on the viewing user's affinity to the users, retrieves images of the selected users, and send the images to the client device. The client device customizes the background and foreground animations based on the images and the viewing user's reaction icon to generate a compound animation for display to the viewing user.

Abstract: An online system communicates a lead generation message to a client device associated with a user. The lead generation message includes a selectable option authorizing a third-party entity to open a channel of communication with the user. If the online system receives from the client device an interaction with the selectable option, the online system sends a notification to the third-party entity indicating that the user associated with the client device interacted with the lead generation content item. The third-party entity may then send a request to the online system to send a message to the user via a messaging system controlled by the online system. The online system thus enables the third-party entity to communicate with the user via the messaging system. The online system then uses information about the communication to train a model to optimize the selection of lead generation messages to users.

Abstract: The present disclosure includes receiving, by a server (1), experience information via a telecommunications network (3) from each of terminals (3) carried by respective users (A to E), the experience information being information regarding an experience desired by each of the users; extracting, in the server, two or more users to generate a single community for the experience information of the two or more users, the two or more users transmitting the experience information having a similarity level not less than a predetermined threshold; extracting, in the server, a destination (5) associated with the experience information having the similarity level not lower than the predetermined threshold using a database (17) configured to preliminarily store the experience information and the destination in association with each other; and transmitting the destination from the server via the telecommunications network to the terminals carried by the two or more users who constitute the single community.

Abstract: Systems and methods for automated test data microservices are provided. Test versions of software (such as an Application Programming Interface (API)) may be configured to automatically generate test data and to call a microservice to manage the test data. The microservice may automatically add and remove the test data from an operational data store to facilitate the testing process and to automatically perform setup and teardown stages of the testing process.

Abstract: A method for controlling application enabling includes receiving from a user an indication of data for sharing and an indication of one or more recipients with which to share the data. A multidimensional zone is determined based on the indication of the data and the indication of the one or more recipients. A request from the user to enable an application via a computing device is detected. Data permission requirements of the application are accessed, and a multidimensional coordinate is determined based on the data permission requirements of the application. The multidimensional zone is compared to the multidimensional coordinate, and the user is notified via the computing device of the comparing of the multidimensional zone to the multidimensional coordinate. An affirmation of the request is received from the user via the computing device, and the application is enabled responsive to the affirmation of the request.

Abstract: Techniques are described for fulfilling resources demand dynamically. In one example method, a query associated with a request of a demand fulfillment analysis associated with an identification of a plurality of potential persons related to a demand is received. The received query is analyzed to determine an intent of the demand. Based on the determined intent of the demand, algorithms to be applied to an underlying data set are identified, where the underlying data set comprises a collected set of information from a plurality of source systems. The identified algorithms are applied to the underlying data set based on a set of parameters associated with the received query to generate an updated data set from the underlying data set. The updated data set is then clustered to generate a result set from the underlying data set, and a visualization of the result set is generated for presentation.

Abstract: The subject disclosure relates to techniques for providing destination recommendations and improving the user experience of autonomous vehicle riders using sentiment analysis. In some aspects, a process of the disclosed technology includes steps for receiving a ride request, at a computing system of an autonomous vehicle (AV), wherein the ride request comprises trip information that specifies a pick-up location associated with a user, navigating the AV to the pick-up location to provide ride service for the user, receiving in-cabin sensor data associated with the user, and analyzing the in-cabin sensor data to determine a sentiment score associated with the user. In some aspects, the process can further include steps for generating a destination recommendation based on the trip information and the sentiment score. Systems and computer-readable media are also provided.

Abstract: Techniques are provided for recommending hardware configuration changes using a user satisfaction rating. One method comprises obtaining usage data indicating user activity for users on computing devices; generating a user profile for each user; clustering the users into user clusters based on the user profiles; determining, for a given user cluster, a satisfaction score for each user in the given user cluster based on the obtained usage data for each user on the computing device; providing suggested hardware upgrades for the computing device of a given user in the given user cluster, wherein the given user is selected based on a lower corresponding satisfaction score relative to the satisfaction scores of other users in the given cluster, and wherein the one or more suggested hardware upgrades are based on hardware configurations of other users in the given cluster having a higher corresponding satisfaction score.

Abstract: Various systems, methods, and media for sourcing and recruiting candidates into an interview process are provided. At least one search criterion is received via an interface. A search area of a network is determined based on the at least one search criterion. The search area of the network defines a talent pool. Data from at least one location in the search area of the network is searched based on the at least one search criterion. The data from the at least one location in the search area of the network is aggregated and evaluated to identify at least one candidate from the talent pool. Information of the at least one candidate is displayed or transmitted via the interface. The data includes information displayed at the at least one location, with the data being displayed in association with the at least one candidate.

Abstract: Provided are mechanisms and processes for performing visual search using multi-view digital media representations, such as surround views. In one example, a process includes receiving a visual search query that includes a surround view of an object to be searched, where the surround view includes spatial information, scale information, and different viewpoint images of the object. The surround view is compared to stored surround views by comparing spatial information and scale information of the surround view to spatial information and scale information of the stored surround views. A correspondence measure is then generated indicating the degree of similarity between the surround view and a possible match. At least one search result is then transmitted with a corresponding image in response to the visual search query.

Abstract: Disclosed herein are methods and systems for facilitating information and expertise distribution via a communication network. A method at a first computing device may include receiving a request for information from a second computing device, determining at least one third computing device based on an analysis of the request for information, communicating the request for information to the determined at least one third computing device, receiving a response corresponding to the request for information from the determined at least one third computing device, adjusting a credit level of a user associated with the determined at least one third computing device based on the received response, and communicating the response to the second computing device. The credit level of the user may indicate one or more credits earned by the user.

Abstract: Methods, systems, and media for presenting recommended content based on social cues are provided. In accordance with some embodiments, a method for presenting recommended content is provided comprising: receiving a query associated with a user; generating a list of relevant media content items based on the query; selecting items for presentation to the user based on social relevance scores based on social connections of the user that have consumed a relevant item and contextual relevance scores for each item; causing the selected items to be presented to the user; and indicating that a particular item was consumed by a particular social connection.