ÜRETKEN YAPAY ZEKA MODELLERİNİN TEKNİK ÖZELLİKLERİ VE KULLANICI GERİ BİLDİRİMLERİNİN ANALİZİ: CHATGPT ÖRNEĞİ

Serkan Metin

doi:10.54282/inijoss.1763596

TR EN

ÜRETKEN YAPAY ZEKA MODELLERİNİN TEKNİK ÖZELLİKLERİ VE KULLANICI GERİ BİLDİRİMLERİNİN ANALİZİ: CHATGPT ÖRNEĞİ

Öz

Bu çalışma, üretken yapay zekâ modellerinin teknik özelliklerini ve kullanıcı deneyimlerini bütüncül bir biçimde inceleyerek ChatGPT örneği üzerinden kapsamlı bir analiz sunmaktadır. Üretken yapay zekânın (ÜYZ) temel bileşenleri, transformer tabanlı büyük dil modelleri, GAN ve VAE gibi alternatif üretici mimariler kuramsal arka plan olarak ele alınmıştır. Bu bağlamda çalışmanın özgün katkısı, ÜYZ teknolojilerinin teknik altyapısı ile kullanıcı yorumlarından elde edilen duygu ve şikâyet analizini birlikte değerlendirmesidir. Veri kümesi Kaggle üzerinde yer alan 196.720 kullanıcı yorumundan oluşmakta olup, yorumlara ilişkin puanlar temel alınarak üç sınıflı (pozitif-nötr-negatif) duygu analizi yapılmıştır. TF-IDF, n-gram ve kelime frekans analizleri metinsel örüntüleri ortaya çıkarmış; ardından Karar Ağacı, Naive Bayes, KNN, SVM, MLP ve Rastgele Orman algoritmaları uygulanmıştır. Sonuçlara göre MLP ve Rastgele Orman modelleri %91 doğruluk ile en başarılı sınıflandırıcılar olmuştur. Ayrıca olumsuz yorumlara dayalı tematik şikâyet analizi gerçekleştirilmiş ve beş temel problem alanı hata mesajları, yükleme sorunları, fiyat eleştirileri, eksik cevaplar, görsel destek problemleri belirlenmiştir. Elde edilen bulgular, ChatGPT’nin genel olarak olumlu karşılandığını; ancak teknik kararlılık ve cevap tutarlılığı konularında geliştirmeye ihtiyaç duyulduğunu göstermektedir.

Anahtar Kelimeler

Üretken Yapay Zeka , Duygu Analizi , Veri Madenciliği , Makine Öğrenmesi , ChatGPT

TECHNICAL FEATURES OF GENERATIVE AI MODELS AND ANALYSIS OF USER FEEDBACK: THE CASE OF CHATGPT

Abstract

This study provides a comprehensive analysis of the technical features of generative artificial intelligence (AI) models and user experiences, focusing on ChatGPT as a representative example. The theoretical background covers the core components of generative AI, including transformer-based large language models, GANs, and VAEs. The study’s main contribution lies in jointly evaluating the technical infrastructure of generative AI and the sentiment- and complaint-based insights extracted from user reviews. The dataset consists of 196,720 user comments collected from Kaggle, and a three-class sentiment analysis (positive-neutral-negative) was conducted using the rating scores assigned to each review. TF-IDF, n-gram, and word-frequency analyses were applied to identify textual patterns, followed by the implementation of Decision Tree, Naive Bayes, KNN, SVM, MLP, and Random Forest classifiers. The results indicate that MLP and Random Forest achieved the highest accuracy rates at 91%. Additionally, a thematic complaint analysis was carried out using only negative comments and five major problem categories were identified: error messages, loading issues, pricing concerns, incomplete responses, and limitations related to image-based functionalities. Findings suggest that while ChatGPT is generally perceived positively, improvements are needed in technical stability and response consistency.

Keywords

Generative Artificial Intelligence , Sentiment Analysis , Data Mining , Machine Learning , ChatGPT

Kaynakça

Abdullah, D.M., & Abdulazeez, A.M. (2021). Machine Learning Applications based on SVM Classification: A Review. Qubahan Academic Jorunal, 1(2), 81-90. https://doi.org/10.48161/qaj.v1n2a50
Alawida, M., Mejri, S., Mehmood, A., Chikhaoui, B., & Isaac Abiodun, O. (2023). A comprehensive study of ChatGPT: Advancements, limitations, and ethical considerations in natural language processing and cybersecurity. Information, 14(462), 1–23. https://doi.org/10.3390/info14080462
Alnasrawi, A. M., Alzubaidi, A. M. N., & Al-Moadhen, A. A. (2024). Improving sentiment analysis using text network features within different machine learning algorithms. Bulletin of Electrical Engineering and Informatics, 13(1), 405–412. https://doi.org/10.11591/eei.v13i1.5576
Akgül, E. S., Ertano, C., & Diri, B. (2016). Twitter verileri ile duygu analizi. Pamukkale Üniversitesi Mühendislik Bilimleri Dergisi, 22(2), 106–110. https://doi.org/10.5505/pajes.2015.37268
Atangana, R., Tchiotsop, D., Kenne, G., & Chanel, L. (2020). EEG signal classification using LDA and MLP classifier. Health Informat. Int. J, 9(1), 14-32.
Atılgan, K. Ö., & Yoğurtcu, H. (2021). Kargo firması müşterilerinin Twitter gönderilerinin duygu analizi. Çağ Üniversitesi Sosyal Bilimler Dergisi, 18(1), 31–39.
Ayan, B., Kuyumcu, B., & Ciylan, B. (2019). Detection of Islamophobic tweets on Twitter using sentiment analysis. Gazi University Journal of Science, Part C, 7(2), 495–502. https://doi.org/10.29109/gujsc.561806
Baldania, R. (2018). Sentiment analysis of movie reviews using heterogeneous features. In 2018 2nd International Conference on Electronics, Materials Engineering and Nano-Technology (IEMENTech). https://doi.org/10.1109/IEMENTECH.2018.8465346
Bhavitha, B. K., Anisha, P. R., & Niranjan, N. C. (2017). Comparative study of machine learning techniques in sentimental analysis. In International Conference on Inventive Communication and Computational Technologies, 216–221.
Bozkurt, A. (2023). ChatGPT, üretken yapay zekâ ve algoritmik paradigma değişikliği. Alanyazın, 4(1), 63–72.

Brynjolfsson, E., Li, D., & Raymond, L. R. (2023). Generative AI at work. NBER Working Paper.
Cascella, M., Montomoli, J., Bellini, V., & Bignami, E. (2023). Evaluating the feasibility of ChatGPT in healthcare: An analysis of multiple clinical and research scenarios. Journal of Medical Systems, 47(33), 1–5.
Dang, N. C., Moreno-García, M. N., & Prieta, F. (2020). Sentiment analysis based on deep learning: A comparative study. Electronics, 9(483). https://doi.org/10.3390/electronics9030483
Day, M. Y., & Lin, Y. D. (2017). Deep learning for sentiment analysis on Google Play consumer review. In 2017 IEEE International Conference on Information Reuse and Integration, 382–388.
Deho, B. O., Agangiba, A. W., Aryeh, L. F., & Ansah, A. J. (2018). Sentiment analysis with word embedding. In 2018 IEEE 7th International Conference on Adaptive Science and Technology (ICAST). https://doi.org/10.1109/ICASTECH.2018.8506717
Du, K., Xing, F., Mao, R., & Cambria, E. (2024). Financial sentiment analysis: Techniques and applications. ACM Computing Surveys, 56(9), 1–42. https://doi.org/10.1145/3649451
Hasan, A., Moin, S., Karim, A., & Shamshirband, S. (2018). Machine learning-based sentiment analysis for Twitter accounts. Mathematics and Computers in Application, 23(11). https://doi.org/10.3390/mca23010011
Hussain, I., Zaidi, S. M. H., Khan, U., & Ahmed, A. (2024). Sentiment analysis classification of ChatGPT tweets using machine learning and deep learning algorithms. Journal of Computing and Biomedical Informatics, 8(1). https://doi.org/10.56979/801.2024
Iyengar, K. P., Yousef, M. M. A., Nune, A., Sharma, G. K., & Botchu, R. (2023). Perception of Chat Generative Pre-trained Transformer (Chat-GPT) AI tool amongst MSK clinicians. Journal of Clinical Orthopaedics and Trauma, 44, 102253. https://doi.org/10.1016/j.jcot.2023.102253
Kaswan, K. S., Dhatterwal, J. S., Malik, K., & Baliyan, A. (2023). Generative AI: A review on models and applications. In 2023 International Conference on Communication, Security and Artificial Intelligence (ICCSAI) (pp. 699–704). IEEE. https://doi.org/10.1109/ICCSAI59793.2023.10421601
Kumaş, E. (2021). Türkçe Twitter verilerinden duygu analizi yapılırken sınıflayıcıların karşılaştırılması. ESTUDAM Bilişim Dergisi, 2(2), 1–5.
Malinka, K., Perešíni, M., Firc, A., Hujňák, O., & Januš, F. (2023). On the educational impact of ChatGPT: Is artificial intelligence ready to obtain a university degree? In Proceedings of the 2023 Conference on Innovation and Technology in Computer Science Education (ITiCSE 2023), 47–53. https://doi.org/10.1145/3587102.35888 Mejova, Y. (2009). Sentiment analysis: An overview. Mijwil, M. M., Hiran, K. K., Doshi, R., Dadhich, M., Al-Mistarehi, A., & Bala, I. (2023). ChatGPT and the future of academic integrity in the artificial intelligence era: A new frontier. Al-Salam Journal for Engineering and Technology, 2(2), 116–127. https://doi.org/10.55145/ajest.2023.02.02.015
Minshuo, C., Song, M., Jianqing, F., & Mengdi, W. (2024). Opportunities and challenges of diffusion models for generative AI. National Science Review, 11, 1–23. https://doi.org/10.1093/nsr/nwae348
Mohammadi‑Pirouz, Z., Hajian‑Tilaki, K., Haddat‑Zavareh, M.S., Amoozadeh, A., & Bahrami, S. (2024). Development of decision tree classification algorithms in predicting mortality of COVID‑19 patients. International Journal of Emergency Medicine, 17:126. https://doi.org/10.1186/s12245-024-00681-7
Moldagulova, A., & Sulaiman, R. (2017). Using KNN Algorithm for Classification of Textual Documents . 8th International Conference on Information Technology (ICIT),665-671. https://doi.org/10.1109/ICITECH.2017.8079924
Morris, M. R. (2023). Scientists’ perspectives on the potential for generative AI in their fields. arXiv. https://doi.org/10.48550/arXiv.2304.01420
Özyer, S. T. (2023). Teknolojik ürün inceleme veri akışında Twitter duyarlılık analizi. Dicle Üniversitesi Mühendislik Fakültesi Dergisi, 14(4), 621–627. https://doi.org/10.24012/dumf.1342578
Popoola, G., Abdullah, K. K., Fuhnwi, G. S., & Agbaje, J. (2024). Sentiment analysis of financial news data using TF-IDF and machine learning algorithms. In 3rd IEEE International Conference on AI in Cybersecurity (ICAIC) (Vol. 1, No. 6). https://doi.org/10.1109/ICAIC60265.2024.10433843
Rahat, A.M., Kahir, A., & Masum, A.K.M. (2019). Comparison of Naive Bayes and SVM Algorithm based on Sentiment Analysis Using Review Dataset. 8th International Conference on System Modeling & Advancement in Research Trends, 22nd–23rd November, 266-270.
Qamar, A. M., Alsuhibany, S. A., & Ahmed, S. S. (2017). Sentiment classification of Twitter data belonging to Saudi Arabian telecommunication companies. International Journal of Advanced Computer Science and Applications, 8(1), 395–401. https://doi.org/10.14569/IJACSA.2017.080150
Sandag, G.A. (2020). Application rating prediction on app store using random forest algorithm. Cogito Smart Journal, 6(2), 167-178.
Sengar, S. S., Hasan, A., Kumar, S., & Carroll, F. (2024). Generative artificial intelligence: A systematic review and applications. Multimedia Tools and Applications. https://doi.org/10.1007/s11042-024-20016-1
Shah, M. S., Bhat, M. A., Singh, M. S., Chavan, M. A., & Singh, M. A. (2024). Sentiment analysis. International Journal of Progressive Research in Engineering Management and Science (IJPREMS), 4(4), 1542–1547. https://doi.org/10.58257/IJPREMS33384
Stine, R. A. (2019). Sentiment analysis. Annual Review of Statistics and Its Application, 6, 287–308. Tembhurne, J. V., Lakhotia, K., & Agrawal, A. (2024). Twitter sentiment analysis using ensemble of multi-channel model based on machine learning and deep learning techniques. Knowledge and Information Systems. https://doi.org/10.1007/s10115-024-02256-7
Ünal, A., & Kılınç, İ. (2024). Üretken yapay zekâların iş dünyası üzerine etkilerine ilişkin erken dönem bir değerlendirme. Elektronik Sosyal Bilimler Dergisi, 23(90), 776–797.
Yang, L., Li, Y., Wang, J., & Sherratt, R. S. (2020). Sentiment analysis for e-commerce product reviews in Chinese based on sentiment lexicon and deep learning. IEEE Access, 8, 23522–23530. https://doi.org/10.1109/ACCESS.2020.2969854
Yanying, M., Qun, L., & Yu, Z. (2024). Sentiment analysis methods, applications, and challenges: A systematic literature review. Journal of King Saud University – Computer and Information Sciences, 36, 102048. https://doi.org/10.1016/j.jksuci.2024.102048
Yoldaş, İ. N. (2021). Türkçe metinlerde duygu analizi: Sözlük tabanlı yaklaşım ve insanların tepkilerinin karşılaştırılması. ESTUDAM Bilişim Dergisi, 2(1), 1–6.
Yu, P., Xu, H., Hu, X., & Deng, C. (2023). Leveraging generative AI and large language models: A comprehensive roadmap for healthcare integration. Healthcare, 11(2776). https://doi.org/10.3390/healthcare11202776
Zhang, Y., Pei, H., Zhen, S., Li, Q., & Liang, F. (2023). Chat Generative Pre-Trained Transformer (ChatGPT) usage in healthcare. Gastroenterology and Endoscopy, 1(3), 139–143. https://doi.org/10.1016/j.gande.2023.07.002
Zhu, N., Zou, P., Li, W., & Cheng, M. (2012). Sentiment analysis: A literature review. In Proceedings of the 2012 IEEE ISMOT , 572–576.
Zhu, Q., & Luo, J. (2022). Generative pre-trained transformer for design concept generation: An exploration. In International Design Conference – Design, 1825–1834. https://doi.org/10.1017/pds.2022.185

Ayrıntılar

Birincil Dil

Türkçe

Konular

İş Sistemleri (Diğer)

Bölüm

Araştırma Makalesi

Yazarlar

Serkan Metin ^*
0000-0003-1765-7474
Türkiye

Yayımlanma Tarihi

31 Aralık 2025

Gönderilme Tarihi

12 Ağustos 2025

Kabul Tarihi

16 Aralık 2025

Yayımlandığı Sayı

Yıl 2025 Cilt: 14 Sayı: 2

DOI

https://doi.org/10.54282/inijoss.1763596

IZ

https://izlik.org/JA68UT25WZ

APA

Metin, S. (2025). ÜRETKEN YAPAY ZEKA MODELLERİNİN TEKNİK ÖZELLİKLERİ VE KULLANICI GERİ BİLDİRİMLERİNİN ANALİZİ: CHATGPT ÖRNEĞİ. İnönü Üniversitesi Uluslararası Sosyal Bilimler Dergisi, 14(2), 744-770. https://doi.org/10.54282/inijoss.1763596

ÜRETKEN YAPAY ZEKA MODELLERİNİN TEKNİK ÖZELLİKLERİ VE KULLANICI GERİ BİLDİRİMLERİNİN ANALİZİ: CHATGPT ÖRNEĞİ

Öz

Anahtar Kelimeler

TECHNICAL FEATURES OF GENERATIVE AI MODELS AND ANALYSIS OF USER FEEDBACK: THE CASE OF CHATGPT

Abstract

Keywords

Kaynakça

Ayrıntılar

Birincil Dil

Konular

Bölüm

Yazarlar

Yayımlanma Tarihi

Gönderilme Tarihi

Kabul Tarihi

Yayımlandığı Sayı

DOI

IZ

Kaynak Göster