Information Content Based Semantic Similarity Measure for Concepts Subsumed By Multiple Concepts

85 ABSTRACT: Semantic Similarity relates to computing the similarity between different ontological concepts .Various categories of semantic similarity measures have been proposed to determine how similar are they between any two concepts within ontology. Information Content (IC) measure is one such among the category of measures. We analyze different methods of calculating the IC value for any concept in ontology and discuss the similarity measures which use this IC value. We select the best performing measure based on the previous work done on these measures and present its limitations. We then propose new Information Content based Semantic Similarity Measure which applied on two datasets proving that it performs better and provides more improved similarity value.