Social Media As A Source Of Unbiased News

Abstract

News media are usually biased toward some political views. Also, the coverage of news is limited to news reported by news agencies. Social media is currently a hub for users to report and discuss news. This includes news reported or missed by news media. Developing a system that can generate news reports from social media can give a global unbiased view on what is hot in a given region. In this talk, we present the research work performed in QCRI for two years, which tackle the problem of using social media to track and follow posts on ongoing news in different regions and for different topics. Initially, we show examples of the presence of bias in reporting news by different news media. We then explore the nature of social media platforms and list the research questions that motivated this work. The challenges for tracking topics related to news are discussed. An automatically adapting information filtering approach is presented that allows tracking broad and dynamic topics in social media. This technique enables automatically tracking posts on news in social media while coping with the high changes occurring in news stories. Our developed system, TweetMogaz, is the demoed, which is an Arabic news portal platform that generated news from Twitter. TweetMogaz reports in real-time what is happening in hot regions in the Middle East, such as Syria and Egypt, in the form of comprehensive reports that include top tweets, images, videos, and news article shared by users on Twitter. It also reports news on different topics such as sports. Moreover, Search is enabled to allow users to get news reports on any topic of interest. The demo would be showing www.tweetmogaz.com live, where emerging topics in news would appear live in front of the audience. By the end of the talk, we would show some of the interesting examples that were noticed on the website in the past year. In addition, a quick overview would be presented on one of the social studies, which was carried out based on the news trend changes on TweetMogaz. The study shows the changes of people behavior when reporting and discussing news during major political changes such as the one happened in Egypt in July 2013. This work is an outcome of two years of research in the Arabic Language Technology group in Qatar Computing Research Institute. The work is published in the form of six research and demo papers in tier 1 conferences such as SIGIR, CSCW, CIKM, and ICWSM. The TweetMogaz system is protected by two patent applications filed in 2012 and 2014. Currently the website serves around 10,000 users, and the number is expected to significantly increase when officially advertised. Please feel free to visit TweetMogaz website for checking the system live: www.tweetmogaz.com Note: A new release with a better design to the website is expected by the time of the conference