A Novel Gravity Optimization Algorithm for Extractive Arabic Text Summarization

Abstract

An automatic text summarization system mimics how humans summarize by picking the most significant sentences in a source text. However, the complexities of the Arabic language have become challenging to obtain information quickly and effectively. The main disadvantage of the traditional approaches is that they are strictly constrained (especially for the Arabic language) by the accuracy of sentence feature functions, weighting schemes, and similarity calculations. On the other hand, the meta-heuristic search approaches have a feature that tolerates imprecision, gets prohibited results, and is not strictly bound by the above restrictions. This paper used the Gravitational Optimization Algorithm (GOA), a powerful metaheuristic approach based on the law of gravity, to address the challenge of extractive summarizing Arabic texts. The objective function of the GOA algorithm is derived based on sentence significance, such as its length, similarity degree, position, statistical term frequency, and named entity ownership. Essex Arabic Summaries Corpus (EASC) was used to evaluate the proposed method and measured by the Recall-Oriented Understudy for Gisting Evaluation (ROUGE). The proposed approach achieved 68.04% Recall, 58.49% Precision, and 60.05% F1-measure using ROUGE-1, higher than standard summarizers and metaheuristic approaches.