作者: Divyank Barnwal , Siddharth Ghelani , Rohit Krishna , Moumita Basu , Saptarshi Ghosh
关键词:
摘要: Microblogging sites are increasingly playing an important role in real-time disaster management. However, rumors and fake news often spread on such platforms, which if not detected, can derail the rescue operations. Therefore, it becomes imperative to verify some of information posted social media during situations. To this end, is necessary correctly identify fact-checkable posts, so that their content be verified. In present work, we address problem identifying posts Twitter microblogging site. We organized a shared task FIRE 2018 conference study identification tweets particular event (the 2015 Nepal earthquake). This paper describes dataset used task, compares performance different methodologies for tweets. primarily experiment with two types approaches - classification-based ranking-based. Our experiments show hybrid methodology involving both classification ranking performs well outperforms employ only or ranking.