#Brexit Vs. #Stopbrexit: What is Trendier? An NLP Analysis

摘要

Online trends have established themselves as a new method of information propagation that isreshaping journalism in the digital age. We argue that sentiment analysis—the classification ofhuman emotion expressed in text—can enhance existing algorithms for trend discovery. Byhighlighting topics that are polarised, sentiment analysis can offer insight into the influence ofusers who are involved in a trend, and how other users adopt such a trend. As a case study, wehave investigated a highly topical subject: Brexit, the withdrawal of the United Kingdom fromthe European Union. We retrieved an experimental corpus of publicly available tweets referringto Brexit and used them to test a proposed algorithm to identify trends. We validate theefficiency of the algorithm and gauge the sentiment expressed on the captured trends to confirmthat highly polarised data ensures the emergence of trends.