Evaluation of Average Term Occurrences Weighting Technique for Arabic Textual Information Retrieval

Abstract

Information retrieval of documents is an important process in the current time, and the vector space retrieval model uses a term weighting scheme as a basic method for matching queries with documents. Term frequency-Inverse document frequency is a widely used and famous term weighting scheme, and many studies proved its effectiveness in information retrieval. However, this term weighting scheme has some drawbacks like retrieving irrelevant documents, which sometimes reduces effectiveness. From this point, a new term weighting scheme called Term Frequency with Average Term Occurrence was proposed and experienced in the English language to minimize retrieving unnecessary documents. In this paper, an information retrieval system is built for the Arabic language, and Open-Source Arabic Corpora was used to complete experiments. Calculations were made using two schemes which are traditional Term frequency-inverse Document Frequency and proposed Term Frequency with Average Term Occurrence. After that, comparisons of results were made using evaluation measures. With all obtained queries, four case studies with two approaches (stop word removal and stemming) are implemented. In English experiments, stop word removal was applied with another discriminative approach, which calculates the centroid of documents. After the analysis of the results, it was found that the proposed scheme is applicable on Arabic text and applied approaches enhance IR effectiveness if they are both implemented. Furthermore, it was found that stop word removal has a favorable effect on both schemes which was also proved in English experiments.