Mining Twitter for Insights into ChatGPT Sentiment: A Machine Learning Approach
Shivam Sharma, Rahul Aggarwal, Manoj Kumar
Abstract
In the past few years, ChatGPT has evolved into a powerful N.L.P. technology, with applications ranging from text generation to question resolution. However, there is still relatively little research on how the public perceives this technology. In this research, we use sentiment analysis techniques to assess the sentiment of tweets regarding ChatGPT. Users manually categorized a dataset of tweets mentioning ChatGPT as positive, negative, or indifferent based on their attitude. The overall sentiment of the tweets was therefore directly determined utilizing machine learning models including logistic regression and support vector machines. Our results show that the majority of tweets related to ChatGPT are neutral, while a smaller proportion are positive or negative. We also found that certain words and phrases, such as "AI" and "language model", are strongly associated with positive sentiment, while others, such as "bias" and "privacy", are associated with negative sentiment. These findings have important implications for the development and deployment of ChatGPT and other NLP technologies, as they suggest that public perception is influenced by factors such as trust, transparency, and ethical considerations. Overall, this paper highlights the importance of understanding public sentiment towards emerging technologies like ChatGPT, and the potential of sentiment analysis techniques to shed light on these issues