Abstract
We propose a concept search system called Kanshinji Antenna that searches for documents with semantic content similar to that of the input text. In this system, concept vectors are statistically generated as the semantic expressions of words, and the similarities between documents are judged based on these concept vectors. This makes it possible to provide search functions that cannot be implemented in ordinary keyword search systems. In this article we discuss the system configuration and useful functions of the Kanshinji Antenna and discuss its effectiveness based on the results of an accuracy evaluation and an online questionnaire.
Notes
1 A Japanese word, Kanshinji means the matter a user is interested in. Kanshinji Antenna metaphorically means the equipment, which catches the user's interest on the Web where news articles and blog postings are continuously distributed.
Nomura, N. (1999). ConceptBase—A NL-based IT Solution Core (IPSJ SIG Tech. Rep. No. NL-129; pp. 1–8). Information Processing Society of Japan.