Affiliation:
1. The Hong Kong Polytechnic University, China
Abstract
This paper proposes semantic TFIDF, an agent-based system for retrieving location-aware information that makes use of semantic information in the data to develop smaller training sets, thereby improving the speed of retrieval while maintaining or even improving accuracy. This proposed method first assigns intelligent agents to gathering location-aware data, which they then classify, match, and organize to find a best match for a user query. This is done using semantic graphs in the WordNet English dictionary. Experiments will compare the proposed system with three other commonly used systems and show that it is significantly faster and more accurate.
Reference28 articles.
1. Baciu, G., Wang, Y., Yao, Y., Chan, K., Kinsner, W., & Zadeh, L. A. (Eds.). (2009, June). In Proceedings of the 8th IEEE International Conference on Cognitive Informatics (ICCI'09), Hong Kong. Washington, DC: IEEE Computer Society Press.
2. Brown, C. M., & Danzig, B. B. (2004). The harvest information discovery and access system. In Proceedings of the 2nd International World Wide Web Conference.
3. Danesh, A., Moshiri, B., & Fatemi, O. (2007). Improve text classification accuracy based on classifier fusion methods. In Proceedings of the Information Fusion, 2007 10th International Conference (pp. 1-6).
4. Davis, J., & Goadrich, M. (2006). The Relationship Between Precision-Recall and ROC Curves. In Proceedings of the ACM 23rd International Conference on Machine learning (pp. 233-240).