EMOTIVE - Extracting the Meaning Of Terse Information in a geo-Visualisation of Emotion

Lead Research Organisation: Loughborough University
Department Name: Information Science

Abstract

The ability for ordinary people to express and exchange their opinions and feelings has increased beyond all expectations in the past ten years of internet expansion and availability. To the military and national security agencies this has provided both opportunities and challenges. Opportunities have emerged in the sense of readily available awareness of discontent and oppositional movements and initiatives. Recent urban disturbances have illustrated the key role played by social networks in the fast-moving events of Summer 2011. The challenges have escalated due to the sheer number of sources of social interaction and public communication media. This research addresses some of these issues in a bold initiative to combine well established and considered science with the increasingly familiar tools of Web 2.0.

Four of the most popular sources of the public exchange of ideas (email, social networks, such as Facebook, microblogs, such as Twitter and comments to newspaper editorials and high-profile stories) will be selectively monitored. Sensitive words and phrases which may be of concern to the military and national security agencies will be extracted by extending a Natural Language Processing technique already developed for email by the Principal Investigator. The team will develop an ontology (a rule-based linguistic database) in which the extracted words and phrases will be semantically filtered and restricted to a manageable set of agreed terms. An example of how the ontology will work can be illustrated by suggesting the number of ways the word 'looting' might be expressed in, for example, established vocabulary (raiding, pillaging, ransacking, etc.) as well as in urban and regional street language and text speak ( doin' over, scamming, etc.). The ontology will be trained to recognise the words and phrases, make semantic links between them and deliver one or more accepted descriptors to the analysts.

EMOTIVE will monitor the traffic of sensitive words and phrases filtered through the ontology when applied to specific incidents, individuals and groups. Increased activity will be indicated by frequency of occurrence or severity, which will be presented through a concept cloud which uses the size of words as a metaphor for frequency and hence importance.

Further to this, a second ontology will be created in which words and phrases that express emotion will be harnessed and this ontology will process the emotionally charged words and phrases extracted from the four sources described above in a similar way to the first

The output of both ontologies will be linked, so that the monitoring analyst will be presented with a colour-coded indication of the strength of emotion attached to the language-based terms.
The final feature in Emotive will be a geo interface to point to the location of the emotionally charged traffic. This interface will be refreshed every 60 seconds with the effect of helping to identify sensitive hot spots of communication and activities. Outputs from the system consisting of effectively presented new knowledge will enable defence and national security agencies both to predict and monitor selected events as they develop and will assist in the formulation of policy.

It can be argued that the general public will be direct beneficiaries of this research in that the defence and national security agencies who act as guardians of public safety and order will be further equipped by this tool to identify, evaluate and ultimately safeguard the public from potentially harmful events.

Defence and national agencies will already be experienced at monitoring these data sources but this tool adds an extra filter of analysis, it will work in almost real time, will amalgamate data from several sources if desired and will provide harmonised output.

Planned Impact

This research will contribute primarily to defence/national security. It offers a means to identify and analyse communication traffic in the context of rapidly moving events. It is now the norm for critical events to be planned, discussed and even conducted via social networking sites. Monitoring staff will be enabled to identify increasing communications on a topic not only by frequency measures but also by interpreting the strength of feeling via the emotional charge in the exchanges, thus adding a powerful and more holistic aspect to the analysis.

Outputs from the system consisting of effectively presented new knowledge will enable defence and national security agencies both to predict and monitor selected events as they develop and will assist in the formulation of policy.

These agencies are already be experienced at monitoring such data sources but this tool adds an extra filter of analysis, it will work in almost real time, will amalgamate data from several sources if desired and provides harmonised output.

The research has the potential for wider impact subject to the agreement of the primary funders. The demonstrator developed could have an important impact in the area of law and order and policing. Applications of the research can be envisaged with rapidly unfolding events such as the Olympic Games, Occupy London or the recent civil disturbances, where the scrutiny of social networks was crucial. The PI's strong research partnerships with the police can contribute to further collaborative initiatives.

Local authorities and government departments could use the tool to observe, collect and act upon customer comments on their websites and other web presences. Both positive and negative indicators will be readily available from the concept cloud.

State funded cultural organisations similarly rely on data to evaluate community engagement through the participation of users of their web and social network presence. Although the real time feature of the tool would not be essential in this context, there is the potential to tailor response to user reaction linked to high profile exhibitions, e.g., the need to increase the number of late opening based on demand.
Similar impact can be envisioned in the commercial sector where there is a vital need to understand, collect and interpret customer reaction to products and services. Most small, medium and global companies have extensive social network presence for marketing and customer engagement.

It can be argued that the general public will be direct beneficiaries of this research in that the defence and national security agencies who act as guardians of public safety and order will be further equipped by this tool to identify, evaluate and ultimately safeguard the public from potentially harmful events.
 
Description EMOTIVE can scan up to 2,000 tweets per second and extract from each a direct expression of one of eight basic emotions: anger, disgust, fear, happiness, sadness, surprise, shame and confusion. Through Twitter it can geographically map the emotional mood of the nation and its reaction to major events. Given any incident, fellings expressed on Twitter can be collated in real time and tracked to monitor changes as the event develops. The ontology employed gives a rich linguistic context to the eight emotions through its ability to analyse both ordinary speech and slang. This ability to monitor how the public mood changes over time is particularly useful when assessing what interventions are most successful in dealing with civil unrest or concern.
Exploitation Route EMOTIVE has many potential applications in society, including use by the police and security services in identifying and tracking potential criminal behaviour or threats to public safety and also in assisting in policy formulation of the best way to react to major incidents. EMOTIVE as a stand-alone system can identify, extract and present a scenario of the emotional temperature of an event as it appears on Twitter over time. As part of a larger event detection sytem it can add the depth of fine-grained emotion interpretation to a complex analysis, such as the prediction of individual and group behaviour in emerging public events.
Sectors Digital/Communication/Information Technologies (including Software),Security and Diplomacy
URL http://emotive.lboro.ac.uk/
 
Description The research is currently being used by the MoD. In addition to this the research has been opened up as a service to organisations. The web site to access the service is http://emotive.systems Another of organisations have asked to see the system working and we are currently working with those organisations.
First Year Of Impact 2012
Sector Aerospace, Defence and Marine,Digital/Communication/Information Technologies (including Software),Retail
Impact Types Societal,Economic
 
Description ReDites: Real Time, Detection, Tracking, Monitoring and Interpretation of Events in Social Media
Amount £241,834 (GBP)
Funding ID EP/L010690/1 
Organisation Engineering and Physical Sciences Research Council (EPSRC) 
Sector Academic/University
Country United Kingdom of Great Britain & Northern Ireland (UK)
Start 06/2013 
End 02/2014
 
Description ReDites Collaboration 
Organisation University of Edinburgh
Country United Kingdom of Great Britain & Northern Ireland (UK) 
Sector Academic/University 
PI Contribution The ReDites project is the result of several projects funded under DaISY being brought together by Dstl and EPSRC to develop a demonstrator capable of bringing together isolated strands of research on event detection, monitoring, interpretation, tracking and visualisation into a single system capable of situation awareness. It is a collaboration between the Universities of Edinburgh, Glasgow, Loughborough, Aston and Sheffield.
Start Year 2013