NGram Approach for Semantic Similarity on Arabic Short Text

Measuring the semantic similarity between words requires a method that can simulate human thought. The use of computers to quantify and compare similarities has become an important research area in various fields, including artificial intelligence, knowledge management, information re-trieval, natural language processing. Computational seman-tics require efficient measures for computing concept similarity, which still need be developed. Several computational based on resources such as WordNet taxonomy. taxonom-ical parameters have been applied optimize expression content semantics. This paper presents new measure quantifying concepts, words, sentences, short text, long text NGram features Synonyms related same domain. proposed algorithm was tested 700 tweets, values were compared with cosine dataset. results analyzed manually by domain expert who concluded provided better than within selected regarding datasets’ texts.