TY  - JOUR
T1  - Sentiment Analysis on GPT-4 with Comparative Models Using Twitter Data
AU  - Özel, Mustafa
AU  - Çetinkaya Bozkurt, Özlem
PY  - 2024
DA  - June
Y2  - 2024
DO  - 10.26650/acin.1418834
JF  - Acta Infologica
JO  - ACIN
PB  - Istanbul University
WT  - DergiPark
SN  - 2602-3563
SP  - 23
EP  - 33
VL  - 8
IS  - 1
LA  - en
AB  - Every day, people from all over the world use Twitter to talk about many different topics using hashtags. Since ChatGPT was launched, researchers have been studying how people perceive it in society. This research aims to find out what Turkish Twitter users think about OpenAI’s latest AI model called Generative Pre-trained Transformer 4 (GPT-4). The quantitative data used in this study consist of hashtags on the topic of GPT-4 and involve 2,978 tweets on this topic that were shared on Twitter between March 14-April 9, 2023. The study uses TextBlob sentiment scores to classify the tweets and support vector machines, logistic regression, XGBoost, and random forest algorithms to classify the sentiment of the dataset. The results from the logistic regression, XGBoost, and support vector methods are in close alignment. All parameter findings indicate dependable machine learning, emphasizing the models’ success in classifying tweet sentiment.
KW  - Sentiment analysis
KW  - social media
KW  - Twitter
KW  - natural language processing
CR  - Abdullah M., Madain A., & Jararweh Y. (2022). ChatGPT: fundamentals, applications and social impacts. 2022 Ninth International Conference on Social Networks Analysis, Management and Security (SNAMS). 1-8. http://dx.doi.org/10.1109/SNAMS58071.2022.10062688 google scholar
CR  - Ağralı, Ö., & Aydın, Ö. (2021). Tweet classification and sentiment analysis on metaverse related messages,. Journal of Metaverse, 1(1), 25-30. google scholar
CR  - Aydın, C. (2018). makine öğrenmesi algoritmalari kullanilarak itfaiye istasyonu ihtiyacinin siniflandirilmasi. Avrupa Bilim ve Teknoloji Dergisi, (14), 169-175. google scholar
CR  - Aydın, Ö., & Karaarslan, E. (2023). Is ChatGPT leading generative AI? What is beyond expectations?. 1-23. Social Science Research Network (SSRN): https://ssrn.com/abstract=4341500 or http://dx.doi.org/10.2139/ssrn.4341500. google scholar
CR  - Ayhan, S., & Erdoğmuş, Ş. (2014). Destek vektör makineleriyle siniflandirma problemlerinin çözümü için çekirdek fonksiyonu seçimi. Eskişehir Osmangazi Üniversitesi İktisadi ve İdari Bilim Dergisi, 9(1), 175-198. google scholar
CR  - Agarwal, B., Mittal, N., Bansal, P., & Garg, S. (2015). Sentiment analysis using common-sense and context information. Computational İntelligence and Neuroscience, 2015, 1-9. http://dx.doi.org/10.1155/2015/715730 google scholar
CR  - Bayram, İ., & Turan, A. (2022). Türkiye’de kripto para farkindaliği ve tutumu: duygu analizi ve istatistiksel analiz ile bir değerlendirme. Yönetim Bilişim Sistemleri Dergisi, 8(2), 20-35. https://dergipark.org.tr/en/pub/ybs/issue/75943/1197985 google scholar
CR  - Bengesi S., Oladunni T., Olusegun R., & Audu H. (2023). A Machine Learning-Sentiment Analysis on Monkeypox Outbreak: An Extensive Dataset to Show the Polarity of Public Opinion From Twitter Tweets, IEEE Access, 11( 11811-11826). http://dx.doi.org/10.1109/ACCESS.2023.3242290 google scholar
CR  - Bircan, H. (2004). Lojistik regresyon analizi: Tıp verileri üzerine bir uygulama. Kocaeli Üniversitesi Sosyal Bilimler Dergisi, (8), 185-208. google scholar
CR  - Biltawi, M., Etaiwi, W., Tedmori, S., Hudaib, A., & Awajan, A. (2016). Sentiment classification techniques for arabic language: A survey. 7th International Conference on Information and Communication Systems (ICICS), 339-346. google scholar
CR  - Botchu, R., & Iyengar, K. P. (2023). Will ChatGPT drive radiology in the future?. Indian Journal of Radiology and Imaging. https://doi.org/10.1055/s-0043-1769591 google scholar
CR  - Bruns, A., & Burgess, J. E. (2011). The use of Twitter hashtags in the formation of ad hoc publics. Paper presented at the 6th European Consortium for Political Research General Conference, 25 - 27 August 2011, University of Iceland, Reykjavik. http://eprints.qut.edu.au/46515/ google scholar
CR  - Dandekar, A. R., Shrotri, A.P., Hargude, N.V., Awate, P.P., & Patil, N.D. (2018,August). The rise of social media and its impact. Internatıonal Journal of Research And Analytıcal Revıews 5(3), 882-886. google scholar
CR  - Diyasa, I. G. S. M., Mandenni, N. M. I. M., Fachrurrozi, M. I., Pradika, S. I., Manab, K. R. N., & Sasmita, N. R. (2021). Twitter sentiment analysis as an evaluation and service base on python textblob. In IOP Conference Series: Materials Science and Engineering, 1125(1), 1-12. https://doi.org/10.1088/1757-899X/1125/1/012034 google scholar
CR  - Doğan, G. (2022). Makine öğrenmesi algoritmalari ile betonarme kirişlerin burulma momenti tahmini. El-Cezeri El-Cezerî Fen ve Mühendislik Dergisi, 9(2), 912-924. google scholar
CR  - Feng, Y., Vanam, S., Cherukupally, M., Zheng, W., Qiu, M., & Chen, H. (2023). Investigating code generation performance of chatgpt with crowdsourcing social data. In Proceedings of the 47th IEEE Computer Software and Applications Conference, 1-10. google scholar
CR  - Hardeniya, T., & Borikar, D. A. (2016). Dictionary based approach to sentiment analysis-a review. International Journal of Advanced Engineering, Management and Science, 2(5), 317-322. google scholar
CR  - Kahya, A. N. (2021). Wikipedia’daki verilere metin madenciliği yöntemlerinin uygulanmasi. Eskişehir Türk Dünyası Uygulama ve Araştırma Merkezi (ESTUDAM) Bilişim Dergisi, 2(1), 11-14. google scholar
CR  - Kaur C., & Sharma A. (2022). Social issues sentiment analysis using python. 2020 5th International Conference on Computing, Communication and Security (ICCCS), 1-6. http://dx.doi.org/10.1109/ICCCS49678.2020.9277251 google scholar
CR  - Keskin, E. K. (2023). Yapay zekâ sohbet robotu ChatGPT ve Türkiye internet gündeminde oluşturduğu temalar. Yeni Medya Elektronik Dergisi, 7(2), 114-131. google scholar
CR  - Kirmani, A. R. (2022), Artificial Intelligence-Enabled Science Poetry. ACS Energy Letters, 8, 574-576. https://doi.org/10.1021/acsenergylett.2c02758 google scholar
CR  - Korkmaz, A., Aktürk, C., & Talan, T. (2023). Analyzing the user’s sentiments of ChatGPT using twitter data. Iraqi Journal for Computer Science and Mathematics, 4(2), 202-214. google scholar
CR  - Koubaa, A. (2023). GPT-4 vs. GPT-3.5: A concise showdown. Preprint. https://doi.org/10.20944/preprints202303.0422.v1 google scholar
CR  - Küçükkartal, H. K. (2020). Twitter’daki verilere metin madenciliği yöntemlerinin uygulanması. Eskişehir Türk Dünyası Uygulama ve Araştırma Merkezi Bilişim Dergisi, 1(2), 10-13. google scholar
CR  - Lampropoulos, G., Ferdig, R. E., & Kaplan-Rakowski, R. (2023). A social media data analysis of general and educational use of chatgpt: understanding emotional educators. Available at SSRN: https://ssrn.com/abstract=4468181 or http://dx.doi.org/10.2139/ssrn.4468181 google scholar
CR  - Li, L., Ma, Z., Fan, L., Lee, S., Yu, H., & Hemphill, L. (2023). ChatGPT in education: A discourse analysis of worries and concerns on social media, 1-35. arXiv preprint arXiv:2305.02201. google scholar
CR  - Liu, Y., Han, T., Ma, S., Zhang, J., Yang, Y., Tian, J., ... & Ge, B. (2023). Summary of ChatGPT/GPT-4 research and perspective towards the future of large language models. 1-35. arXiv preprint arXiv: 2304.01852. https://doi.org/10.48550/arXiv.2304.01852. google scholar
CR  - Lund, B.D., & Wang, T. (2023). Chatting about ChatGPT: How may AI and GPT impact academia and libraries? Library Hi Tech News, 40(3), 26-29. https://doi.org/10.1108/LHTN-01-2023-0009. google scholar
CR  - Metlek, S., & Kayaalp, K. (2020). Derin öğrenme ve destek vektör makineleri ile görüntüden cinsiyet tahmini. Düzce Üniversitesi Bilim ve Teknoloji Dergisi, 8(3), 2208-2228. google scholar
CR  - Munggaran, J. P., Alhafidz, A. A., Taqy, M., Agustini, D. A. R., & Munawir, M. (2023). Sentiment analysis of twitter users’ opinion data regarding the use of ChatGPT in education. Journal of Computer Engineering, Electronics and Information Technology, 2(2), 75-88. google scholar
CR  - Rachman F. H., Imamah, & Rintyarna B. S. (2022). Sentiment analysis of madura tourism in new normal era using text blob and KNN with hyperparameter tuning. 2021 International Seminar on Machine Learning, Optimization, and Data Science (ISMODE), 23-27. http://dx.doi.org/10.1109/ISMODE53584.2022.9742894 google scholar
CR  - Ulaş, M., & Karabay, B. (2020). Terör saldırılarını içeren büyük verinin makine öğrenmesi teknikleri ile analizi. Fırat Üniversitesi Mühendislik Bilimleri Dergisi, 32(1), 267-277. google scholar
CR  - Okoloegbo, C. A., Eze, U. F., Chukwudebe, G. A., & Nwokonkwo, O. C. (2022). Multilingual Cyberbullying Detector (CD) Application for Nigerian Pidgin and Igbo Language Corpus. In 2022 5th Information Technology for Education and Development (ITED), 1-6. https://doi.org/10.1109/ITED56637.2022.10051345 google scholar
CR  - OpenAI (2023). GPT-4 Technical Report. https://cdn.openai.com/papers/gpt-4.pdf. google scholar
CR  - Rahman, S., Jahan, N., Sadia, F., & Mahmud, I. (2023). Social crisis detection using twitter based text mining-a machine learning approach, BULLETIN OF ELECTRICAL ENGINEERING AND INFORMATICS, 12(2), 1069-1077. https://doi.org/10.11591/eei.v12i2.3957 google scholar
CR  - Santra, A. K., & Christy, C. J. (2012). Genetic algorithm and confusion matrix for document clustering. International Journal of Computer Science Issues (UCSI), 9(1), 322-328. google scholar
CR  - Shinde, P. P., & Shah, S. (2018). A review of machine learning and deep learning applications. In 2018 Fourth İnternational Conference on Computing Communication Control And Automation (ICCUBEA), 1-6. https://doi.org/10.1109/iccubea.2018.8697857 google scholar
CR  - Suh, B., Hong, L., Pirolli, P., & Chi, E. H. (2010). Want to be retweeted? Large scale analytics on factors impacting retweet in Twitter network. In 2010 Second İnternational Conference on Social Computing, 177-184. google scholar
CR  - Tekin, R., & Yaman, O. (2023). Akıllı ev sistemleri için XGBoost tabanlı saldırı tespit yöntemi. Journal of Intelligent Systems: Theory and Applications, 6(2), 152-158. https://doi.org/10.38016/jista.1075054 google scholar
CR  - Turan, A. K., & Polat, H. (2024). Yarı denetimli makine öğrenmesi yöntemini kullanarak müzik türlerinin tespiti. Gazi University Journal of Science Part C: Design and Technology, 12(1), 92-107. https://doi.org/10.29109/gujsc.1352477 google scholar
CR  - Veranyurt, Ü., Deveci, A., Esen, M. F., & Veranyurt, O. (2020). Makine öğrenmesi teknikleriyle hastalık sınıflandırması: Random forest, k-nearest neighbour ve adaboost algoritmaları uygulaması. Uluslararası Sağlık Yönetimi ve Stratejileri Araştırma Dergisi, 6(2), 275-286. google scholar
CR  - Verma, A., Mittal, V., & Dawn, S. (2019). FIND: Fake information and news detections using deep learning. In 2019 Twelfth İnternational Conference On Contemporary Computing (IC3), 1-7. https://doi.org/10.1109/IC3.2019.8844892 google scholar
CR  - Wankhade, M., Rao, A. C. S., & Kulkarni, C. (2022). A Survey on sentiment analysis methods, applications, and challenges. Artificial Intelligence Review, 55(7), 5731-5780. google scholar
CR  - Zahoor, S., & Rohilla, R. (2020). Twitter sentiment analysis using lexical or rule based approach: a case study. In 2020 8th International Conference on Reliability, Infocom Technologies and Optimization (Trends and Future Directions) (ICRITO), 537-542. google scholar
CR  - Zhang, L., Wang, S., & Liu, B. (2018). Deep learning for sentiment analysis: A survey. Wiley Interdisciplinary Reviews: Data Mining and Knowledge Discovery, 8(4), 1-25. google scholar
UR  - https://doi.org/10.26650/acin.1418834
L1  - https://dergipark.org.tr/en/download/article-file/3656433
ER  -