Social Media Analysis with GATE
Diana Maynard
Department of Computer Science, University of Sheffield
Bio:
Diana Maynard has been a Research Fellow at the University of Sheffield, UK since February 2000, after acquiring a PhD in Natural Language Processing from Manchester Metropolitan University. Her main interests are in information extraction, opinion mining, sarcasm detection, social media, terminology and semantic web technologies. She is the chief developer of Sheffield University's open-source Information Extraction tools, and currently leads the work on Information Extraction and Opinion Mining on the EU DecarboNet project. She is chair of the annual GATE training course, and leads the GATE consultancy on IE and opinion mining. She has published extensively, organised a number of national and international conferences, workshops and tutorials, taught at summer schools, and given many invited talks and keynotes.
Abstract:
Can Twitter predict my chances of getting flu? Is social media causing deterioration in English skills? How much should I trust hotel reviews online? What's the best helpline to use in Who Wants to be a Millionaire? These days there is an increasing need to interpret and act upon information from large-volume, social media streams, such as Twitter, Facebook, and forum posts. While analysis of longer documents (e.g. news) has been very well studied, understanding social media content has only recently been addressed. Social media poses three major computational challenges, dubbed by Gartner the 3Vs of big data: volume, velocity, and variety. Text analysis methods, in particular, face further difficulties arising from the short, noisy, and strongly contextualised nature of social media. To address the 3Vs of social media, novel language technologies have emerged, e.g. using locality sensitive hashing to detect new stories in media streams (volume), predicting stock market movements from tweet sentiment (velocity), and recommending blogs and news articles based on users' own comments (variety). In this talk I will discuss some of the main problems for social media language analysis, and explain how the GATE tools can be used to deal with them, based around the core topics of information extraction and sentiment analysis.