Semantic information retrieval on the web

Sezer E., Yazici A., Yarimagan U.

ADVANCES IN INFORMATION SYSTEMS, PROCEEDINGS, cilt.4243, ss.158-167, 2006 (SCI-Expanded) identifier identifier

  • Yayın Türü: Makale / Tam Makale
  • Cilt numarası: 4243
  • Basım Tarihi: 2006
  • Doi Numarası: 10.1002/int.20153
  • Dergi Adı: ADVANCES IN INFORMATION SYSTEMS, PROCEEDINGS
  • Derginin Tarandığı İndeksler: Science Citation Index Expanded (SCI-EXPANDED), Scopus, Compendex, EMBASE, MathSciNet, Philosopher's Index, zbMATH
  • Sayfa Sayıları: ss.158-167
  • Hacettepe Üniversitesi Adresli: Evet

Özet

In this study, a semantic information retrieval system to access web content is proposed. Web pages existing in the web contain not only textual but also visual data. When textual and visual data are combined, the semantics of the information presented in a web page becomes richer. Consequently, types of text body and visual data are queried as one entity in a single query sentence to improve the precision, recall and r(norm) parameters of a web query. Fuzzy domain ontology to fill the gap between raw content and semantic features is used, and a model namely OAC (Object, Action and Concept) is proposed. The core of our system is the OAC Model used for fuzzy domain ontology derivation. The OAC Model serves both images and texts, equally. Several experiments are carried out on selected real web pages, and good results are obtained.