6 June 2013 in IEEE Transactions on Multimedia
Online social and news media generate rich and timely information about real-world events of all kinds. However, the huge amount of data available, along with the breadth of the user base, requires a substantial effort of information filtering to successfully drill down to relevant topics and events. Trending topic detection is therefore a fundamental building block to monitor and summarize information originating from social sources. There are a wide variety of methods and variables and they greatly affect the quality of results. We compare six topic detection methods on three Twitter datasets related to major events, which differ in their time scale and topic churn rate. We observe how the nature of the event considered, the volume of activity over time, the sampling procedure and the pre-processing of the data all greatly affect the quality of detected topics, which also depends on the type of detection method used. We find that standard natural language processing techniques can perform well for social streams on very focused topics, but novel techniques designed to mine the temporal distribution of concepts are needed to handle more heterogeneous streams containing multiple stories evolving in parallel. One of the novel topic detection methods we propose, based on -grams cooccurrence and topic ranking, consistently achieves the best performance across all these conditions, thus being more reliable than other state-of-the-art techniques.
1 September 2002 in Information Processing & Management
25 March 2014 in Digital Journalism
Identifying and verifying new information quickly are key issues for journalists who use social media. This article examines what tools journalists think they need to cope with the growing volume and complexity of news on social media, and what improvements are needed in existing systems. It gives some initial results from a major European Union research project (Social Sensor), involving computer scientists, journalists, and media researchers, that is designing a new tool to search across social media for news stories, to surface trends, and to help with verification. Preliminary results suggest that an effective tool should focus on the role of key influencers, and should be customisable to suit the particular needs of individual journalists and news organisations.
8 December 2014 in ACM SIGCAS Computers and Society
In this paper, the authors discuss sexism and misogyny within video game culture through the lens of two high-profile examples of cyber-mob harassment and vilification of 'girls in gaming'. We discuss the representation of women within games as a set up for a discussion of Anita Sarkeesian and her Women versus Tropes in Games Youtube series. We then discuss indie game developer Zoe Quinn and what has become known online as 'gamergate. We use logs from the participants in Quinn's harassment to deconstruct the anatomy, techniques and methodology of misogynist online harassment, and how it is permitted and normalized by wider gaming culture. We stress that while this is not universal, it is wide-spread, insidious, and a major problem for video gaming culture. We conclude with a short discussion on the ways in which the issue can be addressed.
31 January 2008 in Information Processing & Management