Abstract: Various embodiments of the present invention provide methods, apparatus, systems, computing devices, computing entities, and/or the like for performing text similarity determination. Certain embodiments of the present invention utilize systems, methods, and computer program products that perform text similarity determination by using at least one of Word Mover's Similarity measures, Relaxed Word Mover's Similarity measures, and Related Relaxed Word Mover's Similarity measures.

Abstract: There is a need for more effective and efficient natural language processing (NLP) solutions. This need can be addressed by, for example, solutions for performing NLP-based document prioritization by utilizing joint sentiment-topic (JST) modeling.

Abstract: A system and method for automatically detecting misinformation is disclosed. The misinformation detection system is implemented using a cross-stitch based semi-supervised end-to-end neural attention model which is configured to leverage the large amount of unlabeled data that is available. In one embodiment, the model can at least partially generalize and identify emerging misinformation as it learns from an array of relevant external knowledge. Embodiments of the proposed system rely on heterogeneous information such as a social media post's text content, user details, and activity around the post, as well as external knowledge from the web, to identify whether the content includes misinformation. The results of the model are produced via an attention mechanism.

Abstract: There is a need for more effective and efficient natural language processing (NLP) solutions. This need can be addressed by, for example, solutions for performing NLP-based document prioritization by utilizing joint sentiment-topic (JST) modeling.

Abstract: Various embodiments of the present invention provide methods, apparatus, systems, computing devices, computing entities, and/or the like for performing text similarity determination. Certain embodiments of the present invention utilize systems, methods, and computer program products that perform text similarity determination by using at least one of Word Mover's Similarity measures, Relaxed Word Mover's Similarity measures, and Related Relaxed Word Mover's Similarity measures.

Abstract: A system and method for automatically detecting misinformation is disclosed. The misinformation detection system is implemented using a cross-stitch based semi-supervised end-to-end neural attention model which is configured to leverage the large amount of unlabeled data that is available. In one embodiment, the model can at least partially generalize and identify emerging misinformation as it learns from an array of relevant external knowledge. Embodiments of the proposed system rely on heterogeneous information such as a social media post's text content, user details, and activity around the post, as well as external knowledge from the web, to identify whether the content includes misinformation. The results of the model are produced via an attention mechanism.

Abstract: There is a need for more effective and efficient natural language processing (NLP) solutions. This need can be addressed by, for example, solutions for performing NLP-based document prioritization by utilizing joint sentiment-topic (JST) modeling.

Abstract: An online system provides a feed of content including organic content items and sponsored content items that are positioned relative to each other to maximize user interaction with the feed of content. To reduce latency of providing the feed of content to a user without impairing positioning of organic content items and sponsored content items relative to each other, the online system generates the feed of content including organic content items and sends the feed of content to a client device while selecting sponsored content items for the feed of content. The online system transmits selected sponsored content items to the client device, which modifies the feed of content to include the sponsored content items and presents the modified feed of content.

Abstract: There is a need for more effective and efficient natural language processing (NLP) solutions. This need can be addressed by, for example, solutions for performing NLP-based document prioritization by utilizing joint sentiment-topic (JST) modeling.

Abstract: A social networking system dynamically adjusts a number of advertisements presented to a user along with organic content items by modifying a ranking including organic content items and advertisements. Partial engagement scores are generated for organic content items based on an expected amount of user interaction with each organic content item, and scores are generated for advertisements based on expected user interaction and bid amounts associated with each organic content item. An engagement score measuring the user's estimated interaction with a content feed including organic content items without advertisements and an additional engagement score measuring the user's estimated interaction with a content feed including organic content items and advertisements are determined from the partial engagement scores and the scores.

Abstract: An online system accesses a content item containing a link to an external landing page. When an opportunity to present content to a viewing user occurs, the system determines a quality metric for the content item. The system further determines, based on the attributes of the external page, a quality metric for the external page. The quality metric for the external page is adjusted based on the quality metric of the content item. The system computes a value score for the content item based on the quality metrics for the content item and the external page. The content item is ranked against other content items for presentation in the opportunity. Content items are selected by the system and sent for presentation to the viewing user.

Abstract: An online system generates one or more models that determine a likelihood of a user interacting with an application over a particular time interval after installing the application. To generate the one or more models, the online system obtains information describing a user's interaction with the application that occurred greater than a threshold time period prior to a time for which user interaction with the application is to be determined. Example user interactions with the application include: usage of the application, numbers of particular interactions with the application, an amount of compensation the application receives from the user, interactions with other users of the application via the application, and any other suitable interactions. Various engagement metrics may be predicted by the one or more models such as an amount of time spent using the application, particular actions taken in the application, and revenue generated by the user in the application.

Abstract: An online system provides a feed of content including organic content items and sponsored content items that are positioned relative to each other to maximize user interaction with the feed of content. To reduce latency of providing the feed of content to a user without impairing positioning of organic content items and sponsored content items relative to each other, the online system initially selects a subset of sponsored content items based on characteristics (e.g., bid amounts) of the sponsored content items. Subsequently, the online system applies one or more selection processes to organic content items and to sponsored content items of the subset that accounts for positioning of sponsored content items and organic content items relative to each other within the feed of content. Hence, the online system evaluates the subset of sponsored content items along with organic content items when ordering content within the feed.

Abstract: An online system accesses a plurality of posts associated with a quality metric used to subsidize or penalize an associated bid amount when competing for presentation. Each of the plurality of posts receives a quality rating from a professional rating service. The professional quality rating is considered to be ground truth. A mathematical function is used to describe the relationship between the professional quality rating and the quality metric determined by the system. The plurality of posts is segmented into categories. Based on whether the categories of posts fall above or below the mathematical function by more than a threshold amount, the system identifies an unfair subsidy or penalty associated with the category of content and adjusts the associated quality metric accordingly.

Abstract: A social networking system dynamically adjusts a number of advertisements presented to a user along with organic content items by modifying a minimum bid amount associated with advertisements eligible for presentation to the user. Increasing the minimum bid amount decreases the number of advertisements presented to the user while decreasing the minimum bid amount increases the number of advertisements presented to the user. An engagement score measuring the user's estimated interaction with a content feed including organic content items without advertisements and an engagement score measuring the user's estimated interaction with a content feed including organic content items and advertisements are determined. A target score is determined based on the engagement scores, and a difference between the target score and a threshold value is used to modify a minimum price of advertisements eligible for presentation to the user.

Abstract: An online system provides a feed of content including organic content items and sponsored content items that are positioned relative to each other to maximize user interaction with the feed of content. To reduce latency of providing the feed of content to a user without impairing positioning of organic content items and sponsored content items relative to each other, the online system generates the feed of content including organic content items and sends the feed of content to a client device while selecting sponsored content items for the feed of content. The online system transmits selected sponsored content items to the client device, which modifies the feed of content to include the sponsored content items and presents the modified feed of content.

Abstract: Methods and systems are described herein for predicting the quality of content items for display to a user of an online system. The method involves training a model to predict user values for content items based on ratings provided by a panel of professional raters for a set of content items. The trained model receives embeddings for a viewing user of the online system and for a page associated with a content item along with edge factors representing the viewing user's interactions on the online system and generates a user value representing the predicted quality of the content item for the viewing user. The method further involves combining the predicted user value with a user interaction score for the content item to generate a content item score used to determine whether to display the content item to the viewing user.

Abstract: An online system provides a feed of content including organic content items and sponsored content items that are positioned relative to each other to maximize user interaction with the feed of content. To reduce latency of providing the feed of content to a user without impairing positioning of organic content items and sponsored content items relative to each other, the online system initially selects a subset of sponsored content items based on characteristics (e.g., bid amounts) of the sponsored content items. Subsequently, the online system applies one or more selection processes to organic content items and to sponsored content items of the subset that accounts for positioning of sponsored content items and organic content items relative to each other within the feed of content. Hence, the online system evaluates the subset of sponsored content items along with organic content items when ordering content within the feed.

Abstract: An online system generates one or more models that determine a likelihood of a user interacting with an application over a particular time interval after installing the application. To generate the one or more models, the online system obtains information describing a user's interaction with the application that occurred greater than a threshold time period prior to a time for which user interaction with the application is to be determined. Example user interactions with the application include: usage of the application, numbers of particular interactions with the application, an amount of compensation the application receives from the user, interactions with other users of the application via the application, and any other suitable interactions. Various engagement metrics may be predicted by the one or more models such as an amount of time spent using the application, particular actions taken in the application, and revenue generated by the user in the application.

Abstract: A social networking system dynamically adjusts a number of advertisements presented to a user along with organic content items by modifying a ranking including organic content items and advertisements. Partial engagement scores are generated for organic content items based on an expected amount of user interaction with each organic content item, and scores are generated for advertisements based on expected user interaction and bid amounts associated with each organic content item. An engagement score measuring the user's estimated interaction with a content feed including organic content items without advertisements and an additional engagement score measuring the user's estimated interaction with a content feed including organic content items and advertisements are determined from the partial engagement scores and the scores.