Harnessing Linked Knowledge Sources for Topic Classification in Social Media
Dr Elizabeth Cano Basave

This event took place on 3rd April 2013 at 11:30am (10:30 GMT)
Knowledge Media Institute, Berrill Building, The Open University, Milton Keynes, United Kingdom, MK7 6AA

Topic classification (TC) of short text messages o ffers an effective and fast way to reveal events happening around the world ranging from those related to Disaster (e.g. Sandy hurricane) to those related to Violence (e.g. Egypt revolution). In this talk I will present a novel approach for harnessing concept graph structures surrounding entities appearing on microposts. This approach involves the following steps: (i) building a conceptual representation of entities presented in different Knowlege sources (KS)s, (ii) leveraging contextual information about concepts by exploiting semantic concept graphs, and (iii) providing a principled way for the combination of KSs. Experiments evaluating our TC classifier in the context of Violence detection (VD) and Emergency Responses (ER) show promising results that significantly outperform various baseline models including an approach using a single KS without linked data and an approach using only Tweets.


The webcast was open to 100 users

Click below to play the event (48 minutes)

Creative Commons Licence KMi logo