Yahoo! Inc.

Oath Inc.

Excalibur Ip, LLC

Yahoo Assets LLC

Shirin Oskooi

Dan S Pelleg

David Carmel

Yoelle Smadja Maarek

Idan Szpektor

Oleg Rokhlenko

Yuval David Pinter

Somesh Jain

Archit Shrivastava

Samiksha Harish Kothari

Methods and devices for assessing the quality of user-generated content are described. In one embodiment, a method is disclosed for measuring the quality of a user-generated answer to a question by combining various factors, including question-answer surface word vector similarity, question-answer explicit semantic analysis vector similarity, answer-answer explicit sematic analysis vector similarity, query performance predictor, sentiment analysis, textual analysis of the answer, and reputation of the answerer. The method uses a learning procedure to determine the best algorithm for measuring the overall quality of the answer based on these factors.

Quality-based scoring and inhibiting of user-generated content

Users may engage with content that may invoke various emotions. For example, a user may find an image as inspirational, a social network post as funny, etc. Accordingly, content may be labeled with user emotion labels, specified by users that engaged with the content, to create labeled content (e.g., the image may be labeled as inspirational). Emotional transition triggers may be defined for users (e.g., 30 minutes of a user writing a school report using a word processing application). Responsive to a triggering of an emotional transition trigger, labeled content may be provided to a user (e.g., the image may be provided to the user as an inspirational break from writing the school report). In this way, content may be labeled based upon emotions that the content invokes in users, and such labeled content may be provided to users in a contextually relevant manner (e.g., a study break).

Emotionally relevant content

Growing community of inventors

San Francisco, CA, United States of America

Shirin Oskooi