EKNOT: Event Knowledge from News and Opinions on Twitter

We present the EKNOT system that automatically discovers major events from online news articles, connects each event to its discussion on Twitter, and provides a comprehensive summary of the events from both news media and social media’s point of view. EKNOT takes a time period as input and outputs a complete picture of what happened and the public’s opinions. For each event, EKNOT provides multi-dimensional summaries: a) a summary from news for an objective description; b) a summary from tweets containing opinions/sentiments; c) an en- tity graph which illustrates the major players involved and their correlations; d) the time span of the event; and e) an opinion (sentiment) distribution. A user-friendly interface is provided to facilitate interactive exploration of the mining results: if a user is interested in a particular event, he/she can zoom in this event to investigate its multiple aspects (sub-events). These aspects will be summarized in the same way with the above features. Furthermore, EKNOT is built on real-time crawled news articles and tweets. The efficient data collection and processing scheme allows users to explore the dynamics of major events from the perspectives of both news and social media in near real-time.

Name thesis:degree_name

M.S.

Level thesis:degree_level

Thesis

Discipline thesis:degree_discipline

Computer Science

Grantor

University of Illinois at Urbana-Champaign

Year dc:date

2015

Author dc:creator

• Li, Min

• system
• event discovery

Statement dc:rights

• Copyright 2015 Min Li

Language dc:language

en

Handle dc:identifier

http://hdl.handle.net/2142/78673

OAI identifier oai:identifier

oai:www.ideals.illinois.edu:2142/78673