Skip to main content

Research Repository

See what's under the surface

Real-time topic detection with bursty n-grams: RGU's submission to the 2014 SNOW challenge.

Martin, Carlos; Goker, Ayse

Authors

Carlos Martin

Ayse Goker



Abstract

Twitter is becoming an ever more popular platform for discovering and sharing information about current events, both personal and global. The scale and diversity of messages makes the discovery and analysis of breaking news very challenging. Nonetheless, journalists and other news consumers are increasingly relying on tools to help them make sense of Twitter. Here, we describe a fully-automated system capable of detecting trends related to breaking news in real-time. It identifies words or phrases that `burst' with sudden increased frequencies, and groups these into topics. It identifies a diverse set of recent tweets that are related to these topics, and uses these to create a suitable human-readable headline. In addition, images coming from the diverse tweets are also added to the topic. Our system was evaluated using 24 hours of tweets as part of the Social News On the Web (SNOW) 2014 data challenge.

Start Date Apr 8, 2014
Publication Date Apr 28, 2014
Print ISSN 1613-0073
Publisher CEUR Workshop Proceedings
Pages 9-16
Series ISSN 1613-0073
Institution Citation MARTIN, C. and GOKER, A. 2014. Real-time topic detection with bursty n-grams: RGU's submission to the 2014 SNOW challenge. In Proceedings of the 2014 Social news on the web data challenge (SNOW-DC 2014), 8th April 2014, Seoul, Korea. Seoul: CEUR-WS [online], pages 9-16. Available from http://ceur-ws.org/Vol-1150/martin.pdf
Keywords Twitter; Current events; News; Social networking; Journalists; Breaking news; Bursts
Publisher URL http://ceur-ws.org/Vol-1150/martin.pdf

Files







Downloadable Citations