2015/05/30 by Gerasimos Razis, Ioannis Anagnostopoulos, Razis, Gerasimos +1
Computer Science · Physics and Astronomy · #Complex Network Analysis Techniques #Semantic Web and Ontologies #Web Data Mining and Analysis #cs.SI
paper · pdf · doi:10.48550/arxiv.1506.00100
Draft version of paper. arXiv admin note: substantial text overlap with arXiv:1409.3771
arxiv created 2015/05/30 · arxiv updated 2015/06/02
On daily basis, millions of Twitter accounts post a vast number of tweets including numerous Twitter entities (mentions, replies, hashtags, photos, URLs). Many of these entities are used in common by many accounts. The more common entities are found in the messages of two different accounts, the more similar, in terms of content or interest, they tend to be. Towards this direction, we introduce a methodology for discovering and suggesting similar Twitter accounts, based entirely on their disseminated content in terms of Twitter entities used. The methodology is based exclusively on semantic representation protocols and related technologies. An ontological schema is also described towards the semantification of the Twitter accounts and their entities.