Abstract
Context: Educational data mining (EDM) is a growing field that utilizes machine learning, statistics, and data mining to analyze data from educational settings. Its applications include classifying and predicting students’ performance and dropouts, predicting teachers’ performance, and improving the learning process. A crucial aspect of EDM is student sentiment analysis, which involves analyzing digital text to determine the emotional tone of messages.

Objective: This article aims to leverage data mining techniques and algorithms to analyze educational data and identify trends and insights that can enhance personalized learning experiences. Specifically, the objective is to analyze students’ sentiments based on their semester grades, providing valuable insights into their emotional state and learning experiences.

Materials/Methods: In this study, machine learning classifiers are employed to measure the sentiment of students. Various algorithms, including simple linear regression, multiple linear regression, ridge regression, lasso regression, elastic net regression, polynomial regression, and support vector machine algorithms, are utilized for sentiment analysis.

Conclusion: Our research contributes to the field by integrating the principles of process control into educational data mining and sentiment analysis, which is a novel approach in the context of personalized learning. By incorporating process control methodologies, we dynamically monitor and regulate the learning process based on student sentiments. Through meticulous data analysis and algorithm selection, our study provides insights into the relationship between student emotions, learning behaviors, and academic outcomes. This work underscores the significance of leveraging data mining techniques to enhance personalized learning experiences, offering tailored recommendations and interventions to foster improved academic outcomes and engagement.