Sentiment Analysis on GPT-4 with Comparative Models Using Twitter Data

Every day, people from all over the world use Twitter to talk about many differenttopics using hashtags. Since ChatGPT was launched, researchers have been study-ing how people perceive it in society. This research aims to find out what TurkishTwitter users think about OpenAI's latest AI model called Generative Pre-trainedTransformer 4 (GPT-4). The quantitative data used in this study consist of hashtagson the topic of GPT-4 and involve 2,978 tweets on this topic that were shared onTwitter between March 14-April 9, 2023. The study uses TextBlob sentiment scoresto classify the tweets and support vector machines, logistic regression, XGBoost, andrandom forest algorithms to classify the sentiment of the dataset. The results from thelogistic regression, XGBoost, and support vector methods are in close alignment. Allparameter findings indicate dependable machine learning, emphasizing the models'success in classifying tweet sentiment