Upgrading domain ontology based on latent semantic analysis and group center similarity calculation
Rung-Ching Chen, I-Yan Lee, Y.-K. Lee, Yu-Lung Lo · Conference proceedings/Conference proceedings - IEEE International Conference on Systems, Man, and Cybernetics · 2008
In this paper, we will propose a domain ontology extensible method which can insert new keywords into the corresponding constructed domain ontology. The novel method uses TF-IDF (Term Frequency - Inverse Document Frequency) and LSA (Latent Semantic Analysis) to strengthen the semantic characteristic of keywords and transform the LSA matrix into a high dimensional space based on collected web pages. The similarity between keywords and concepts is evaluated by comparing the keywords on high dimensional matrix to the corresponding constructed ontology group center and individual concept. The keyword which has the highest similarity with the domain concept will be inserted into the offspring of the concept on the domain ontology and will become a new domain concept. The primary experiment uses the existing Chinese basketball ontology to examine its precision and the experimental results indicate that our proposed method has 73% accuracy.