Twittener: Improving News Experience with Sentiment Analysis and Trend Recommendation

The Internet provides a profusion of online sources for both trending topics and news. With the vast content made available, it might risk readers in information overloading before finding all relevant contents and thus perceive this medium as challenging and overwhelming. Most of the available news sites provide content from official news sites and exclude posts on social media. This paper presents a web application, Twittener, an improved news aggregator that enhances users’ reading experience and time-efficiency when reading news online, with the implementation of text-to-speech technology, sentiment analysis and hybrid recommender system. This paper also presents a user study that was conducted to determine the factors that increase the acceptance rate of such a system by the public based on the Technology Acceptance Model (TAM).