A semantic metric for concepts similarity in knowledge graphs

Semantic similarity between concepts concerns expressing the degree of similarity in meaning between two concepts in a computational model. This problem has recently attracted considerable attention from researchers in attempting to automate the understanding of word meanings to expedite the classification of users' opinions and attitudes embedded in text. In this article, a semantic similarity metric is presented. The proposed metric, namely, weighted information-content (wic), exploits the information content of the least common subsumer of two compared concepts and the depth information in knowledge graphs such as DBPedia and YAGO. The two similarity components were combined using calibrated cooperative contributions from both similarity components. A statistical test using the Spearman correlations on well-known human judgement word-similarity data sets showed that the wic metric produced more highly correlated similarities compared with state-of-the-art metrics. In addition, a real-world aspect category classification was evaluated, which exhibited further increased accuracy and recall.