Characterising Emergent Semantics in Twitter Lists
published: July 4, 2012, recorded: May 2012, views: 3624
Report a problem or upload filesIf you have found a problem with this lecture or would like to send us extra material, articles, exercises, etc., please use our ticket system to describe your request and upload the data.
Enter your e-mail into the 'Cc' field, and we will keep you updated with your request's status.
Twitter lists constitute a form of organising Twitter users into sets, and can be created and maintained by any user in Twitter. In this paper we describe a characterisation approach of the emergent semantics in these lists, which consists in deriving semantic relations between lists and users by analyzing the co-occurrence of keywords in list names. We use the vector space model and Latent Dirichlet Allocation to obtain similar keywords according to co-occurrence patterns. These results are then compared to similarity measures relying on the WordNet synset hierarchy and to existing Linked Data sets. Results show that co-occurrence of keywords based on members of the lists produce more synonyms and more correlated results to that of WordNet similarity measures.
Download slides: eswc2012_garcia_silva_semantics_twitter_01.pdf (1.9 MB)
Link this pageWould you like to put a link to this lecture on your homepage?
Go ahead! Copy the HTML snippet !