METHODS FOR IMPROVING USABILITY OF ONLINE USER GENERATED CONTENT

Abstract

User Generated Content in forms of reviews, numeric ratings, blogs, posts in forum and social media are present in an overwhelming amount to help users make informed decisions about various products or services. Although helpful, many of these posts are not accurate, and might be biased by an individual’s opinion or idiosyncratic experiences. This limits their usability as general reliable information sources. In this thesis, we propose a range of data driven methods to automatically handle inherent subjectivity in user opinions. We devise new frameworks based on probabilistic graphical models as well as neural networks. We have validated our models by using them for practical applications such as, (1) quantifying the aspect biases of users to better interpret their observed ratings, (2) retrieving supporting reviews for an individual’s opinion to facilitate consensus modeling, (3) predicting user specific drug side effects, and (4) detecting veracity of rumors on social media.