An improved similarity computation module based on basic semantics and influencing factors of concepts in domain ontology

The concepts in domain ontology have similarities, and a good similarity computation method can improve the efficiency of information retrieval system and recommendation system. The current similarity computation methods of concepts in domain ontology do not take full account of the structural information carried by the concept nodes, and their performance are still room for improvement. On the basis of studying the existing similarity computation methods, we propose an improved similarity computation module of concepts in domain ontology which based on basic semantics and influencing factors (BISCM). BISCM takes the similarities of semantic distance, information content (IC) and attribute between concepts as the basic semantics to conduct the similarity computation, then considers 3 kinds of influencing factors to adjust the similarity and get the final similarity. The influencing factors include the level sequence, hierarchy depth and the coincidence degree of nodes. The experimental results show that BISCM perfects the factors needed to be considered in the concepts similarity computation; the Pearson correlation between the similarities computed by BISCM between expert experiences ups to 95.1% and BISCM has well adaptability to computing the similarities of concepts in domain ontology.