In particular, the Arabic text on social media provides a wealth of information about consumer sentiment, attitudes, and behavior, as digital change occurs more quickly than ever. Examining this form of text is difficult because of the morphological complexity of the Arabic language and its dialect variability. Deep learning models were employed to address these challenges to classify Arabic social media comments into satisfaction, loyalty, purchase intention, and service quality. Modern deep learning techniques, such as Arabic Bidirectional Encoder Representations from Transformers (AraBERT) and Bidirectional Long Short-Term Memory Network (BiLSTM), are used in this research. The results demonstrate the importance of the models employed, with AraBERT yielding the best results across all measurements concerning the unbalanced dataset. Meanwhile, when it comes to a balanced dataset, the BiLSTM performs slightly better than AraBERT. This research provides evidence to support the viability of these models for the classification of short Arabic text. It lays a foundation for applying the deep learning model to derive insights from Jordanian dialect’s social media comments. The impact of the balanced dataset on the performance of deep learning models is also confirmed by this research.

[1] Abd D., Khan W., Khan B., Alharbe N., and et al., “Categorization of Arabic Posts Using Artificial Neural Network and Hash Features,” Journal of King Saud University-Computer and Information Sciences, vol. 35, no. 6, pp. 102733, 2023. DOI: 10.1016/j.jksus.2023.102733

[2] Aftan S. and Shah H., “Using the AraBERT Model for Customer Satisfaction Classification of Telecom Sectors in Saudi Arabia,” Brain Sciences, vol. 13, no. 1, pp. 1-20, 2023. DOI: 10.3390/brainsci13010147

[3] Alammary A., “BERT Models for Arabic Text Classification: A Systematic Review,” Applied Sciences, vol. 12, no. 11, pp. 5720, 2022. DOI: 10.3390/app12115720

[4] Alhawarat M. and Aseeri A., “A Superior Arabic Text Categorization Deep Model,” IEEE Access, vol. 8, pp. 24653-24661, 2020. https://doi.org/10.1109/ACCESS.2020.2970504

[5] Al-Laith A., Shahbaz M., Alaskar H., and Rehmat A., “Arasencorpus: A Semi-Supervised Approach for Sentiment Annotation of a Large Arabic Text Corpus,” Applied Sciences, vol. 11, no. 5, pp. 2434, 2021. DOI: 10.3390/app11052434

[6] Almuzaini H. and Azmi A., “Impact of Stemming and Word Embedding on Deep Learning-based Arabic Text Categorization,” IEEE Access, vol. 8, pp. 127913-127928, 2020. DOI: 10.1109/ACCESS.2020.3009217

[7] Alnagi E., Ghnemat R., and Abu Al-Haija Q., “Boosting Arabic Text Classification Using Hybrid Deep Learning Approach,” Discover Applied Sciences, vol. 7, no. 540, 2025. https://doi.org/10.1007/s42452-025-07025-x

[8] Al-Qerem A., Raja M., Taqatqa S., and Abu Sara M., “Utilizing Deep Learning Models (RNN, LSTM, CNN-LSTM, and Bi-LSTM) for Arabic Text Classification,” Artificial Intelligence- Augmented Digital Twins, vol. 503, pp. 287-301, 2024. DOI: 10.1007/978-3-031-43490-7_22

[9] Alruily M., Fazal A., Mostafa A., and Ezz M., “Automated Arabic Long-Tweet Classification Using Transfer Learning with BERT,” Applied Sciences, vol. 13, no. 6, pp. 1-17, 2023. DOI: 10.3390/app13063482

[10] Alsemaree O., Alam A., Gill S., and Uhlig S., “Sentiment Analysis of Arabic Social Media Texts: A Machine Learning Approach to Deciphering Customer Perceptions,” Heliyon, vol. 10, no. 9, pp. e27863, 2024. https://www.cell.com/heliyon/fulltext/S2405- 8440(24)03894-5

[11] Alshamari M., “Evaluating User Satisfaction Using Deep-Learning-based Sentiment Analysis for Social Media Data in Saudi Arabia’s Telecommunication Sector,” Computers, vol. 12, no. 9, pp. 1-24, 2023. DOI: 10.3390/computers12090170

[12] Al-Smadi B., “DeBERTa-BiLSTM: A Multi- Label Classification Model of Arabic Medical Questions Using Pre-Trained Models and Deep Learning,” Computers in Biology and Medicine, vol. 170, pp. 107921, 2024, DOI: 10.1016/j.compbiomed.2024.107921

[13] Alsokkar A., Otair M., Alfar H., Nasereddin A., and et al., “Sentiment Analysis for Arabic Call Center Notes Using Machine Learning Techniques,” Journal of Autonomous Intelligence, vol. 7, no. 3, pp. 1-16, 2024. DOI: 10.32629/jai.v7i3.940

[14] Alsuwaylimi A., “Arabic Dialect Identification in Social Media: A Hybrid Model with Transformer Models and BiLSTM,” Heliyon, vol. 10, no. 17, pp. 1-18, 2024. DOI: 10.1016/j.heliyon.2024.e36280

[15] Al‐Twairesh N., “The Evolution of Language Models Applied to Emotion Analysis of Arabic Tweets,” Information, vol. 12, no. 2, pp. 1-15, 2021. DOI: 10.3390/info12020084

[16] Alwehaibi A., Bikdash M., Albogmi M., and Roy K., “A Study of the Performance of Embedding Methods for Arabic Short-Text Sentiment Analysis Using Deep Learning Approaches,” Journal of King Saud University-Computer and Information Sciences, vol. 34, no. 8, pp. 6140- 6149, 2022. DOI: 10.1016/j.jksuci.2021.07.011

[17] Alzanin S., Azmi A., and Aboalsamh H., “Short Text Classification for Arabic Social Media Tweets,” Journal of King Saud University- Computer and Information Sciences, vol. 34, no. 9, pp. 6595-6604, 2022. DOI: 10.1016/j.jksuci.2022.03.020

[18] Angdresey A., Sitanayah L., Lucky I., and Tangka H., “Sentiment Analysis for Political Debates on YouTube Comments Using BERT Labeling, Random Oversampling, and Multinomial Naïve Bayes,” Journal of Computing Theories and Applications, vol. 2, no. 3, pp. 342-354, 2025. https://doi.org/10.62411/jcta.11668

[19] Ashisha G., Mary X., Kanaga E., Andrew J., and Eunice R., “Random Oversampling-based Diabetes Classification via Machine Learning Algorithms,” International Journal of 34 The International Arab Journal of Information Technology, Vol. 23, No. 1, January 2026 Computational Intelligence Systems, vol. 17, no. 270, pp. 1-17, 2024. DOI: 10.1007/s44196-024- 00678-3

[20] Ashokkumar P., Arunkumar N., and Don S., “Intelligent Optimal Route Recommendation Among Heterogeneous Objects with Keywords,” Computers and Electrical Engineering, vol. 68, pp. 526-535, 2018. DOI: 10.1016/j.compeleceng.2018.05.004

[21] Bartok L. and Burzler M., “How to Assess Rater Rankings? A Theoretical and a Simulation Approach Using the Sum of the Pairwise Absolute Row Differences,” Journal of Statistical Theory and Practice, vol. 14, no. 37, pp. 1-16, 2020. DOI: 10.1007/s42519-020-00103-w

[22] Bourahouat G., Abourezq M., and Daoudi N., “Word Embedding as a Semantic Feature Extraction Technique in Arabic Natural Language Processing: An Overview,” The International Arab Journal of Information Technology , vol. 21, no. 2, pp. 313-325, 2024. DOI: 10.34028/21/2/13

[23] El Rifai H., Al Qadi L., and Elnagar A., “Arabic Text Classification: The Need for Multi-Labeling Systems,” Neural Computing Applied, vol. 34, no. 2, pp. 1135-1159, 2022. https://doi.org/10.1007/s00521-021-06390-z

[24] Elnagar A., Al-Debsi R., and Einea O., “Arabic Text Classification Using Deep Learning Models,” Information Processing and Management, vol. 57, no. 1, pp. 102121, 2020. https://doi.org/10.1016/j.ipm.2019.102121

[25] Fitriyah Z. and Kartikasari M., “Text Classification of Twitter Opinion Related to Permendikbud 30/2021 Using Bidirectional LSTM,” Barekeng Jurnal Ilmu Matematika Dan TerapaN, vol. 17, no. 2, pp. 1113-1122, 2023. DOI: 10.30598/barekengvol17iss2pp1113-1122

[26] Galal O., Abdel-Gawad A., and Farouk M., “Rethinking of BERT Sentence Embedding for Text Classification,” Neural Computing Applied, vol. 36, no. 32, pp. 20245-20258, 2024. DOI: 10.1007/s00521-024-10212-3

[27] Gupta S. and Zeithaml V., “Customer Metrics and their Impact on Financial Performance,” Marketing Science, vol. 25, no. 6, pp. 718-739, 2006. DOI: 10.1287/mksc.1060.0221

[28] Kankeviciute E., Songailaite M., Mandravickaite J., Kalinauskaite D., and Krilavicius T., “A Comparison of Deep Learning Models for Hate Speech Detection,” in Proceedings of the 27th International Conference on Information Technology, Kaunas, pp. 1-11, 2022. https://ceur- ws.org/Vol-3611/paper19.pdf

[29] Khan M. and AlGhamdi M., “A Customized Deep Learning-based Framework for Classification and Analysis of Social Media Posts to Enhance the Hajj and Umrah Services,” Expert Systems with Applications, vol. 238, pp. 122204, 2024. DOI: 10.1016/j.eswa.2023.122204

[30] Kraidia I., Ghenai A., and Belhaouari S., “A Multi-Faceted Approach to Trending Topic Attack Detection Using Semantic Similarity and Large-Scale Datasets,” IEEE Access, vol. 13, pp. 21005-21028, 2025. DOI: 10.1109/ACCESS.2025.3535996

[31] Kübler R., Adler S., Welke L., and Sarstedt M., “Mining Consumer Mindset Metrics with User- Generated Content,” Schmalenbach Journal of Business Research, vol. 77, pp. 497-525, 2025. DOI: 10.1007/s41471-025-00219-4

[32] Liu C., “Long Short-Term Memory (LSTM)- Based News Classification Model,” PLoS One, vol. 19, no. 5, pp. 1-23, 2024. DOI: 10.1371/journal.pone.0301835

[33] Lu G., Liu Y., Wang J., and Wu H., “CNN- BiLSTM-Attention: A Multi-Label Neural Classifier for Short Texts with a Small Set of Labels,” Information Processing and Management, vol. 60, no. 3, pp. 103320, 2023. DOI: 10.1016/j.ipm.2023.103320

[34] Ma X., Li Y., and Asif M., “E-Commerce Review Sentiment Analysis and Purchase Intention Prediction Based on Deep Learning Technology,” Journal of Organizational and End User Computing, vol. 36, no. 1, pp. 1-29, 2024. DOI: 10.4018/JOEUC.335122

[35] Marshall P., “A Latent Allocation Model for Brand Awareness and Mindset Metrics,” International Journal of Market Research, vol. 64, no. 4, pp. 526-540, 2021. DOI: 10.1177/14707853211040052

[36] Mhamed M., Sutcliffe R., and Feng J., “Benchmark Arabic News Posts and Analyzes Arabic Sentiment Through RMuBERT and SSL with AMCFFL Technique,” Egyption Informatics Journal, vol. 29, pp. 100601, 2025. DOI: 10.1016/j.eij.2024.100601

[37] Mozumder A., Nguyen T., Devi S., Ahmed P., and et al., “Enhancing Customer Satisfaction Analysis Using Advanced Machine Learning Techniques in Fintech Industry,” Journal of Computer Science and Technology Studies, vol. 6, no. 3, pp. 35-41, 2024. DOI: 10.32996/jcsts.2024.6.3.4

[38] Muaad A., Davanagere H., Guru D., Benifa J., and et al., “Arabic Document Classification: Performance Investigation of Preprocessing and Representation Techniques,” Mathematical Problems in Engineering, vol. 2022, no. 1, pp. 1- 16, 2022. DOI: 10.1155/2022/3720358

[39] Oyebode O., Alqahtani F., and Orji R., “Using Machine Learning and Thematic Analysis Methods to Evaluate Mental Health Apps based on User Reviews,” IEEE Access, vol. 8, pp. 111141-111158, 2020. DOI: 10.1109/ACCESS.2020.3002176 Analyzing Consumer Mindset Metrics in Arabic Dialectical Texts on Social Media ... 35

[40] Petersen J., Kumar V., Polo Y., and Sese F., “Unlocking the Power of Marketing: Understanding the Links between Customer Mindset Metrics, Behavior, and Profitability,” Journal of the Academy of Marketing Science, vol. 46, no. 5, pp. 813-836, 2018. DOI: 10.1007/s11747-017-0554-5

[41] Rubera G. and Kirca A., “You Gotta Serve Somebody: The Effects of Firm Innovation on Customer Satisfaction and Firm Value,” Journal of the Academy of Marketing Science, vol. 45, no. 5, pp. 741-761, 2017. DOI: 10.1007/s11747-016- 0512-7

[42] Salloum A. and Almustafa M., “Analysis and Classification of Customer Reviews in Arabic Using Machine Learning and Deep Learning,” Journal of Data Acquisition and Processing, vol. 38, no. 4, pp. 726-744, DOI: 10.5281/zenodo.777803

[43] Savci P. and Das B., “Prediction of the Customers’ Interests Using Sentiment Analysis in E- Commerce Data for Comparison of Arabic, English, and Turkish languages,” Journal of King Saud University-Computer and Information Sciences, vol. 35, no. 3, pp. 227-237, 2023. DOI: 10.1016/j.jksuci.2023.02.017

[44] Shahriar S., Al Roken N., and Zualkernan I., “Classification of Arabic Poetry Emotions Using Deep Learning,” Computers, vol. 12, no. 5, pp. 1- 14, 2023. DOI: 10.3390/computers12050089

[45] Srinivasan S., Vanhuele M., and Pauwels K., “Mind-Set Metrics in Market Response Models: An Integrative Approach,” Journal of Marketing Research, vol. 47, no. 4, pp. 672-684, 2010. DOI: 10.1509/jmkr.47.4.672

[46] Tan P., Receiver Operating Characteristic, Encyclopedia of Database Systems, 10.1007/978- 0-387-39940-9_569, Last Visited, 2025.

[47] Vargas F., Carvalho I., Goes F., Benevenuto F., and Pardo T., “Building an Expert Annotated Corpus of Brazilian Instagram Comments for Hate Speech and Offensive Language Detection,” in Proceedings of the 13th Conference on Language Resources and Evaluation, Marseille, pp. 7174- 7183, 2021. https://aclanthology.org/2022.lrec- 1.777/

[48] Venkatesan R., Bleier A., Reinartz W., and Ravishanker N., “Improving Customer Profit Predictions with Customer Mindset Metrics Through Multiple Overimputation,” Journal of the Academy of Marketing Science, vol. 47, no. 5, pp. 771-794, 2019. DOI: 10.1007/s11747-019- 00658-6

[49] Wahdan A., Al-Emran M., and Shaalan K., “A Systematic Review of Arabic Text Classification: Areas, Applications, and Future Directions,” Soft Computing, vol. 28, no. 2, pp. 1545-1566, 2024. DOI: 10.1007/s00500-023-08384-6

[50] Wongvorachan T., He S., and Bulut O., “A Comparison of Undersampling, Oversampling, and SMOTE Methods for Dealing with Imbalanced Classification in Educational Data Mining,” Informaion, vol. 14, no. 1, pp. 54, 2023. DOI: 10.3390/info14010054

[51] Zaghloul M., Barakat S., and Rezk A., “Predicting E-Commerce Customer Satisfaction: Traditional Machine Learning vs. Deep Learning Approaches,” Journal of Retailing and Consumer Services, vol. 79, pp. 103865, 2024. DOI: 10.1016/j.jretconser.2024.103865