Sentiment Analysis of ChatGPT Tweets Using Machine Learning Techniques

Large language models like ChatGPT by OpenAI have gained significant attention for their impressive performance across various tasks. They have become highly popular among adopters. Gaining an understanding of the sentiment of these adopters is crucial, as it can offer valuable information about the potential outcomes of the technology, whether it will thrive or falter, and the advantages and drawbacks it possesses.In this research, data mining techniques are utilized to analyze Twitter data and automatically categorize their sentiment polarity. A dataset of 15,000 English tweets is gathered in natural language from ChatGPT users, and text mining and data mining techniques are applied to convert them into a useful format. The objective is to build a sentiment classifier capable of predicting whether a tweet conveys positive, negative, or neutral sentiments. To achieve this, we utilize two widely used data mining classifiers: K-Nearest Neighbor and Naive Bayes. These classifiers are applied to analyze the sentiment of the tweets, and their overall accuracy, precision, and recall values are assessed, providing a comprehensive comparison between the two methods.