Domain classification for celebrities using spreading activation and reasoning on semantic network
Dongsheng Wang, Kyunglag Kwon, In-Jeong Chung · 2013
Celebrities are influential nodes in Social Network Services (SNSs) whose domain classification can assist researchers to better analyze normal users' interests. In this paper, we propose an automatic classification method that extracts the celebrity's name and description as the input and the associated domain can be mapped to a domain ontology by performing Spreading activation on the knowledge base and reasoning on the domain ontology. The knowledge base is merged from YAGO ( Wikipedia and WordNet) and WordNet Domain ontology. We fetch 15,879 celebrity profiles, map them to WordNet Domain ontology, and demonstrate a satisfactory result of the mapping ratio.