Sentiment Analysis for Enhancing Student Engagement and Learning Outcomes

This paper presents a comprehensive exploration of sentiment analysis in educational settings, specifically focusing on student feedback analysis to enhance engagement and learning outcomes. Leveraging advanced data science methodologies, including a Convolutional Neural Network (CNN) architecture, the study achieves an impressive accuracy of 96.58% in sentiment classification. The introduction sets the context by highlighting the significance of sentiment analysis in understanding student sentiments, improving instructional strategies, and creating a student-centric learning environment. The paper addresses the problem statement related to the manual and subjective nature of traditional feedback analysis and provides background information on the emergence and applications of sentiment analysis in educational data science. Through a detailed literature review, the study identifies gaps and challenges in existing research while showcasing the transformative potential of sentiment analysis in educational contexts.