{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,21]],"date-time":"2025-09-21T15:38:52Z","timestamp":1758469132873,"version":"3.44.0"},"reference-count":0,"publisher":"Zarqa University","issue":"5","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IAJIT"],"published-print":{"date-parts":[[2025]]},"abstract":"<jats:p>Sentiment Analysis (SA) has become popular for determining opinions and feelings from textual data. The huge amount of text fed to sentiment analysis models can be considered an obstacle that slows the models\u2019 execution. Besides, it requires a large memory to run these models. Thus, data reduction and feature extraction processes can enhance these models\u2019 performance in terms of time complexity and memory usage. However, the reduction process should not affect the classification models\u2019 performance with the sentiment analysis process to split textual data according to its polarity. In this work, we present an analytical study of the role of data reduction techniques in improving analysis time and accuracy conducted on Arabic datasets.  A structured performance assessment of features is produced. The Bidirectional Encoder Representations from Transformers (BERT) models are used as a data reduction tool, and then the performance results of these models are compared to the performance of the Frequency-Inverse Document Frequency (TF-IDF) model.  The results show that the quality of the features extracted via BERT models is more valuable for sentiment analysis tasks and can enhance the required time by eight different classifiers. For example, the performance of the Random Forest classifier was improved by 3% when BERT models were used for feature extraction rather than the TF-IDF method, and the time taken by the Random Forest Classifier (RFC) was reduced to one-tenth compared to its performance when the TF-IDF was used as a feature extraction tool<\/jats:p>","DOI":"10.34028\/iajit\/22\/5\/7","type":"journal-article","created":{"date-parts":[[2025,8,26]],"date-time":"2025-08-26T05:51:44Z","timestamp":1756187504000},"source":"Crossref","is-referenced-by-count":0,"title":["A New Data Reduction Technique for Efficient Arabic Data Sentiment Analysis"],"prefix":"10.34028","volume":"22","author":[{"given":"Remah","family":"Younisse","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Arafat","family":"Awajan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Maram","family":"Bani Younes","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"19944","published-online":{"date-parts":[[2025]]},"container-title":["The International Arab Journal of Information Technology"],"original-title":[],"language":"en","deposited":{"date-parts":[[2025,9,21]],"date-time":"2025-09-21T09:53:56Z","timestamp":1758448436000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.iajit.org\/upload\/files\/A-New-Data-Reduction-Technique-for-Efficient-Arabic-Data-Sentiment-Analysis.pdf"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"references-count":0,"journal-issue":{"issue":"5","published-online":{"date-parts":[[2025]]},"published-print":{"date-parts":[[2025]]}},"URL":"https:\/\/doi.org\/10.34028\/iajit\/22\/5\/7","archive":["Internet Archive"],"relation":{},"ISSN":["2309-4524","1683-3198"],"issn-type":[{"type":"electronic","value":"2309-4524"},{"type":"print","value":"1683-3198"}],"subject":[],"published":{"date-parts":[[2025]]}}}