{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,11]],"date-time":"2026-04-11T13:58:21Z","timestamp":1775915901347,"version":"3.50.1"},"reference-count":51,"publisher":"Association for Computing Machinery (ACM)","issue":"8","license":[{"start":{"date-parts":[[2023,8,24]],"date-time":"2023-08-24T00:00:00Z","timestamp":1692835200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["ACM Trans. Asian Low-Resour. Lang. Inf. Process."],"published-print":{"date-parts":[[2023,8,31]]},"abstract":"<jats:p>ChatGPT OpenAI, a large-language chatbot model, has gained a lot of attention due to its popularity and impressive performance in many natural language processing tasks. ChatGPT produces superior answers to a wide range of real-world human questions and generates human-like text. The new OpenAI ChatGPT technology may have some strengths and weaknesses at this early stage. Users have reported early opinions about the ChatGPT features, and their feedback is essential to recognize and fix its shortcomings and issues. This study uses the ChatGPT tweets Arabic dataset to automatically find user opinions and sentiments about ChatGPT technology. The dataset is preprocessed and labeled using the TextBlob Arabic Python library into positive, negative, and neutral tweets. Despite extensive works for the English language, languages like Arabic are less studied regarding tweet analysis. Existing literature about Arabic tweet sentiment analysis has mainly focused on machine learning and deep learning models. We collected a total of 27,780 unstructured tweets from Twitter using the Tweepy SNscrape Python library using various hash-tags such as # Chat-GPT, #OpenAI, #Chatbot, Chat-GPT3, and so on. To enhance the model\u2019s performance and reduce computational complexity, unstructured tweets are converted into structured and normalized forms. Tweets contain missing values, URL and HTML tags, stop words, punctuation, diacritics, elongations, and numeric values that have no impact on the model performance; hence, these increase the computational cost. So, these steps are removed with the help of Python preprocessing libraries to enhance text quality and consistency. This study adopts Transformer-based models such as RoBERTa, XLNet, and DistilBERT that automatically classify the tweets. Additionally, a hybrid transformer-based model is proposed to obtain better results. The proposed hybrid model is developed by combining the hidden outputs of the RoBERTA and BERT models using a concatenation layer, then adding dense layers with \u201cRelu\u201d activation employed as a hidden layer to create non-linearity and a \u201csoftmax\u201d activation function for multiclass classification. They differ from existing state-of-the-art models due to the enhanced capabilities of both models in text classification. Hybrid models combine the different models to make accurate predictions and reduce bias and enhanced the overall results, while state-of-the-art models are incapable of making accurate predictions. Experiments show that the proposed hybrid model achieves 96.02% accuracy, 100% precision on negative tweets, and 99% recall for neutral tweets. The performance of the proposed model is far better than existing state-of-the-art models.<\/jats:p>","DOI":"10.1145\/3605889","type":"journal-article","created":{"date-parts":[[2023,6,30]],"date-time":"2023-06-30T11:56:38Z","timestamp":1688126198000},"page":"1-23","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":41,"title":["Arabic ChatGPT Tweets Classification Using RoBERTa and BERT Ensemble Model"],"prefix":"10.1145","volume":"22","author":[{"ORCID":"https:\/\/orcid.org\/0009-0005-5751-5528","authenticated-orcid":false,"given":"Muhammad","family":"Mujahid","sequence":"first","affiliation":[{"name":"Department of Computer Science, Khwaja Fareed University of Engineering and Information Technology, Pakistan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-2300-9636","authenticated-orcid":false,"given":"Khadija","family":"Kanwal","sequence":"additional","affiliation":[{"name":"Institute of CS and IT, The Women University Multan, Pakistan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8403-1047","authenticated-orcid":false,"given":"Furqan","family":"Rustam","sequence":"additional","affiliation":[{"name":"School of Computer Science, University College Dublin, Ireland"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6700-719X","authenticated-orcid":false,"given":"Wajdi","family":"Aljedaani","sequence":"additional","affiliation":[{"name":"University of North Texas, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8271-6496","authenticated-orcid":false,"given":"Imran","family":"Ashraf","sequence":"additional","affiliation":[{"name":"Department of Information and Communication Engineering, Yeungnam University, Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2023,8,24]]},"reference":[{"key":"e_1_3_1_2_2","doi-asserted-by":"publisher","DOI":"10.31026\/j.eng.2020.06.07"},{"key":"e_1_3_1_3_2","doi-asserted-by":"publisher","DOI":"10.1007\/s00530-020-00742-w"},{"key":"e_1_3_1_4_2","doi-asserted-by":"publisher","DOI":"10.25046\/aj0601112"},{"key":"e_1_3_1_5_2","doi-asserted-by":"publisher","DOI":"10.1177\/0165551515610513"},{"key":"e_1_3_1_6_2","doi-asserted-by":"publisher","DOI":"10.3390\/make5010003"},{"key":"e_1_3_1_7_2","doi-asserted-by":"publisher","DOI":"10.3390\/bdcc7010016"},{"key":"e_1_3_1_8_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCAIS48893.2020.9096850"},{"key":"e_1_3_1_9_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2020.113497"},{"key":"e_1_3_1_10_2","article-title":"AraGPT2: Pre-trained transformer for Arabic language generation","author":"Antoun Wissam","year":"2020","unstructured":"Wissam Antoun, Fady Baly, and Hazem Hajj. 2020. AraGPT2: Pre-trained transformer for Arabic language generation. arXiv preprint arXiv:2012.15520 (2020).","journal-title":"arXiv preprint arXiv:2012.15520"},{"key":"e_1_3_1_11_2","doi-asserted-by":"publisher","DOI":"10.1007\/s11749-016-0488-0"},{"key":"e_1_3_1_12_2","doi-asserted-by":"publisher","DOI":"10.14257\/ijdta.2014.7.1.06"},{"key":"e_1_3_1_13_2","doi-asserted-by":"publisher","DOI":"10.1148\/radiol.223312"},{"key":"e_1_3_1_14_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.procs.2021.05.072"},{"issue":"72","key":"e_1_3_1_15_2","article-title":"Higher education students\u2019 social media platform preferences for educational purposes","volume":"23","author":"\u00c7elik Birol","year":"2023","unstructured":"Birol \u00c7elik, H\u00fcseyin Uzunboylu, and Nur Demirba\u015f-\u00c7elik. 2023. Higher education students\u2019 social media platform preferences for educational purposes. Revista de Educaci\u00f3n a Distancia (RED) 23, 72 (2023).","journal-title":"Revista de Educaci\u00f3n a Distancia (RED)"},{"key":"e_1_3_1_16_2","doi-asserted-by":"publisher","DOI":"10.1145\/3341161.3344821"},{"key":"e_1_3_1_17_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-88113-9_50"},{"key":"e_1_3_1_18_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-81-322-3972-7"},{"key":"e_1_3_1_19_2","doi-asserted-by":"publisher","DOI":"10.1007\/s10462-022-10386-z"},{"key":"e_1_3_1_20_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-25344-7_13"},{"key":"e_1_3_1_21_2","doi-asserted-by":"publisher","DOI":"10.1017\/S1351324920000601"},{"key":"e_1_3_1_22_2","doi-asserted-by":"publisher","DOI":"10.1155\/2021\/9986920"},{"key":"e_1_3_1_23_2","article-title":"An improved text sentiment classification model using TF-IDF and next word negation","author":"Das Bijoyan","year":"2018","unstructured":"Bijoyan Das and Sarit Chakraborty. 2018. An improved text sentiment classification model using TF-IDF and next word negation. arXiv preprint arXiv:1806.06407 (2018).","journal-title":"arXiv preprint arXiv:1806.06407"},{"key":"e_1_3_1_24_2","first-page":"399","volume-title":"Proceedings of the 7th Arabic Natural Language Processing Workshop (WANLP\u201922)","author":"Farha Ibrahim Abu","year":"2022","unstructured":"Ibrahim Abu Farha and Walid Magdy. 2022. The effect of Arabic dialect familiarity on data annotation. In Proceedings of the 7th Arabic Natural Language Processing Workshop (WANLP\u201922). 399\u2013408."},{"key":"e_1_3_1_25_2","doi-asserted-by":"publisher","DOI":"10.1109\/ESOLEC54569.2022.10009633"},{"key":"e_1_3_1_26_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.wanlp-1.44"},{"key":"e_1_3_1_27_2","article-title":"Comparing scientific abstracts generated by ChatGPT to original abstracts using an artificial intelligence output detector, plagiarism detector, and blinded human reviewers","author":"Gao Catherine A.","year":"2022","unstructured":"Catherine A. Gao, Frederick M. Howard, Nikolay S. Markov, Emma C. Dyer, Siddhi Ramesh, Yuan Luo, and Alexander T. Pearson. 2022. Comparing scientific abstracts generated by ChatGPT to original abstracts using an artificial intelligence output detector, plagiarism detector, and blinded human reviewers. bioRxiv (2022), 2022\u201312.","journal-title":"bioRxiv"},{"key":"e_1_3_1_28_2","doi-asserted-by":"publisher","DOI":"10.1109\/RE.2014.6912257"},{"key":"e_1_3_1_29_2","volume-title":"Stock Trend Prediction Using Deep Learning Models LSTM and GRU with Non-linear Regression","author":"Hadhood Haret","year":"2022","unstructured":"Haret Hadhood. 2022. Stock Trend Prediction Using Deep Learning Models LSTM and GRU with Non-linear Regression. Master\u2019s thesis. It\u00e4-Suomen yliopisto."},{"key":"e_1_3_1_30_2","doi-asserted-by":"publisher","DOI":"10.3390\/app12115547"},{"key":"e_1_3_1_31_2","doi-asserted-by":"publisher","DOI":"10.1080\/17475759.2022.2106289"},{"key":"e_1_3_1_32_2","article-title":"\u201cI think this is the most disruptive technology\u201d : Exploring sentiments of ChatGPT early adopters using Twitter data","author":"Haque Mubin Ul","year":"2022","unstructured":"Mubin Ul Haque, Isuru Dharmadasa, Zarrin Tasnim Sworna, Roshan Namal Rajapakse, and Hussain Ahmad. 2022. \u201cI think this is the most disruptive technology\u201d : Exploring sentiments of ChatGPT early adopters using Twitter data. arXiv preprint arXiv:2212.05856 (2022).","journal-title":"arXiv preprint arXiv:2212.05856"},{"key":"e_1_3_1_33_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.procs.2018.10.466"},{"key":"e_1_3_1_34_2","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2919385"},{"key":"e_1_3_1_35_2","doi-asserted-by":"publisher","DOI":"10.3390\/app9194062"},{"key":"e_1_3_1_36_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.wanlp-1.53"},{"key":"e_1_3_1_37_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.bspc.2017.01.010"},{"key":"e_1_3_1_38_2","article-title":"RoBERTa: A robustly optimized BERT pretraining approach","author":"Liu Yinhan","year":"2019","unstructured":"Yinhan Liu, Myle Ott, Naman Goyal, Jingfei Du, Mandar Joshi, Danqi Chen, Omer Levy, Mike Lewis, Luke Zettlemoyer, and Veselin Stoyanov. 2019. RoBERTa: A robustly optimized BERT pretraining approach. arXiv preprint arXiv:1907.11692 (2019).","journal-title":"arXiv preprint arXiv:1907.11692"},{"key":"e_1_3_1_39_2","article-title":"What is AI chatbot phenomenon ChatGPT and could it replace humans?","author":"Lock S.","year":"2022","unstructured":"S. Lock. 2022. What is AI chatbot phenomenon ChatGPT and could it replace humans? \u2018Book What is AI Chatbot Phenomenon ChatGPT and Could it Replace Humans (2022). https:\/\/www.theguardian.com\/technology\/2022\/dec\/05\/what-is-ai-chatbot-phenomenon-chatgpt-and-could-it-replace-humans. Accessed 09-07-2023.","journal-title":"\u2018Book What is AI Chatbot Phenomenon ChatGPT and Could it Replace Humans"},{"key":"e_1_3_1_40_2","unstructured":"Antony Mayfield. 2008. What is social media. (2008). http:\/\/crmxchange.com\/uploadedFiles\/White_Papers\/PDF\/What_is_Social_Media_iCrossing_ebook.pdf."},{"key":"e_1_3_1_41_2","doi-asserted-by":"publisher","DOI":"10.3390\/app11188438"},{"key":"e_1_3_1_42_2","doi-asserted-by":"publisher","DOI":"10.1145\/3368756.3369078"},{"key":"e_1_3_1_43_2","article-title":"How to construct deep recurrent neural networks","author":"Pascanu Razvan","year":"2013","unstructured":"Razvan Pascanu, Caglar Gulcehre, Kyunghyun Cho, and Yoshua Bengio. 2013. How to construct deep recurrent neural networks. arXiv preprint arXiv:1312.6026 (2013).","journal-title":"arXiv preprint arXiv:1312.6026"},{"key":"e_1_3_1_44_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.214"},{"key":"e_1_3_1_45_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2022.101429"},{"key":"e_1_3_1_46_2","doi-asserted-by":"publisher","DOI":"10.1021\/ci034160g"},{"key":"e_1_3_1_47_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.ipm.2013.08.006"},{"key":"e_1_3_1_48_2","doi-asserted-by":"publisher","DOI":"10.1038\/d41586-023-00288-7"},{"key":"e_1_3_1_49_2","doi-asserted-by":"publisher","DOI":"10.2139\/ssrn.4302443"},{"key":"e_1_3_1_50_2","doi-asserted-by":"publisher","DOI":"10.1109\/I4CT.2014.6914200"},{"key":"e_1_3_1_51_2","doi-asserted-by":"publisher","DOI":"10.1109\/IITA.2009.457"},{"key":"e_1_3_1_52_2","doi-asserted-by":"publisher","DOI":"10.1109\/CSCWD.2013.6581022"}],"container-title":["ACM Transactions on Asian and Low-Resource Language Information Processing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3605889","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3605889","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T16:36:19Z","timestamp":1750178179000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3605889"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,8,24]]},"references-count":51,"journal-issue":{"issue":"8","published-print":{"date-parts":[[2023,8,31]]}},"alternative-id":["10.1145\/3605889"],"URL":"https:\/\/doi.org\/10.1145\/3605889","relation":{},"ISSN":["2375-4699","2375-4702"],"issn-type":[{"value":"2375-4699","type":"print"},{"value":"2375-4702","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,8,24]]},"assertion":[{"value":"2023-03-09","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2023-06-12","order":1,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2023-08-24","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}