Sentiment Analysis of Twitter Users’ Opinion Data Regarding the Use of ChatGPT in Education

Abstract

This article presents a sentiment analysis of Twitter users' opinions regarding the use of ChatGPT in education. ChatGPT, an AI chatbot developed by OpenAI, has gained significant attention for its ability to provide detailed responses across various knowledge domains. However, concerns have been raised about its occasional inclusion of inaccurate information. This study aims to analyze the sentiment of Twitter users' opinions towards ChatGPT in education and evaluate its accuracy. The sentiment analysis process involves data crawling, labelling, preprocessing, sentiment analysis, and evaluation. Data is collected from Twitter using the RapidMiner Studio tool and labelled as positive or negative sentiment based on the presence of positive or negative words. Preprocessing techniques are applied to standardize and reduce the volume of words in the data. The sentiment analysis classification is performed using machine learning algorithms, specifically Naive Bayes and Support Vector Machine (SVM). The accuracy, precision, and recall of the classification models are evaluated. The sentiment analysis results provide insights into Twitter users' overall sentiment towards ChatGPT in education. This study contributes to understanding Twitter users' opinions and sentiments regarding using ChatGPT in education. The findings can be valuable for educators and policymakers in assessing the potential impact of ChatGPT on academic integrity and the educational landscape.