- Measuring emotion in social media to aid security monitoring
A decade of internet expansion has resulted in an unprecedented increase in the public’s ability to express and share their opinions and feelings.
For the military and national security agencies, this has provided both opportunities and challenges.
The readily available awareness of discontent and oppositional movements and initiatives provides the opportunity to tap into public feeling. Recent urban disturbances have illustrated the key role played by social networks in fast-moving events.
On the other hand, challenges have escalated due to the sheer number of sources of social interaction and public communication media.
Loughborough has addressed these issues with EMOTIVE (Extracting the meaning of terse information in a visualisation of emotion).
The project – funded by the EPSRC and Dstl – has developed a means of social media analysis for the Ministry of Defence. By combining well-established science with the increasingly familiar tools of Web 2.0, EMOTIVE suggests a way for analysts to interpret live events and to learn and predict behaviour from previous datasets.
“EMOTIVE Ontology: Extracting Fine-Grained Emotions from Terse, Informal Messages“, won the Outstanding Paper award at the 7th IADIS Intelligent Systems Agents and Data Mining (ISA-DM) conference, in Prague (July 22-24 2013).
Real-time analysis tool
The research underpins the development of an intuitive software system that captures emotion on Twitter and displays this in an intuitive and customisable way.
How EMOTIVE works
Capable of capturing thousands of tweets per second, EMOTIVE analyses social media activity, extracting the emotion using a proprietary technology developed from the EMOTIVE research.