The Effect of Combining Different Semantic Relations on Arabic Text Classification

A massive amount of documents are being posted online every minute. The task of document classification requires extensive background work on the content of documents, where keyword-based matching alone may not be sufficient. Much research has been carried out in several languages that has revealed significant results. However, Arabic documents still pose a great challenge due to the nature of Arabic language. Extracting roots or stems from the breakdown of multiple Arabic words and phrases are an important task that must be completed before applying text classification. The research at hand proposes an algorithm for classifying Arabic-Text documents using semantic relations between words based on an Arabic thesaurus, mainly synonyms, hyperonyms and hyponyms. The experiments conducted in this study evaluated the results using F1-Measure and compared them to results obtained via other existing methods, such as utilizing stemmers and part-of-speech taggers, where it indicated an increment of more than 12.6% for the novel method using semantic relation over other methods. Arabic-WordNet was utilized as a thesaurus for indicating possible relations to be examined. The obtained results indicate that the domain of the semantic web reveals a variety of options for enhancing text classifications, which are highly competitive with current methods. Future work will include identifying best relations to be utilized among the available 20 relations. KeywordsArabic Text classification; Stemmer; Part of Speech; Conceptual features; Semantic relations.