Student Performance Prediction Using Regression Analysis & Feature-Based Opinion Mining on Student Feedback

Abstract

Predicting student performance in higher education is a crucial research area in today's technology-driven world. With advancements in technology, understanding, modeling, and predicting student performance has become increasingly beneficial and essential. However, accurately and robustly designing models for predicting student performance poses significant challenges. This study aims to explore the use of machine learning algorithms to predict student performance in higher education. The study collects and analyses data on various factors, such as student demographics, academic background, extracurricular activities, and engagement, using various machine learning algorithms. This approach can be beneficial for educators in identifying at-risk students and developing personalized interventions to improve their academic outcomes. This study emphasizes the importance of leveraging technology and machine learning techniques to predict and improve student performance in higher education. For educators and decision-makers, it offers insightful information on how to efficiently create interventions that enhance student success.

Feature-based opinion mining on student feedback is an important area of research that aims to extract valuable insights from large volumes of student feedback data. In this study, we performed sentiment analysis on student feedback comments using Natural Language Processing (NLP) approaches.