You are here

Investigation into network community structures, to better identify social processes.

Column 1
Funding Programme or Company Name: 
Industry Fellowship
Funding Body: 
Science Foundation Ireland (SFI)
Much of our thinking and decision making derives from communications and influences operating within the communities in which we operate, and that those communications are moderated and shaped by community specific rules, symbols and habits. This has a few practical consequences: things like sentiment and emotion may be more readily identified when taking community contexts into account, and identified community-centric patterns can tell us things about the operation of the community - things like individual roles, dynamics of people joining/leaving and of community ideas and thinking. Preliminary work suggests strong correlations between community structures in the Twitter mutual follower network and topics in tweet texts. Emotion detection/distant learning multilinguality in text analysis as we have been doing for MixedEmotions. This includes approaches to transfer learning between languages, building multilingual Wordnet’s, experiments and analysis of emoji usage across languages/cultures/age groups, and experiments with development of colloquial lexical resources.
Insight Contact: 
Application Domain: 
Research Group: 
Associated Theme for Application Domain: 
The Discovery Economy-The Analytical Society
The Discovery Economy-Discovery Analytics
Involved Institution: 
National University of Ireland, Galway (NUIG)