Sentiment analysis study of library services using support vector machine methodse

Abstract

Academic institutions' libraries contribute significantly to students' success by giving them access to the information resources they need. Sentiment analysis of library services is crucial in the current digital era to comprehend student perspectives and enhance service quality. The purpose of this study is to assess how XYZ University students feel about the library services thereby applying the Support Vector Machine (SVM) technique. Data obtained through a survey utilizing a Google Form is used in this study to analyze sentiment using the SVM algorithm. Preprocessing steps include data cleaning, normalization, tokenization, stopword removal, and stemming. Eighty percent of the data were used to train the SVM model, while twenty percent of the data were used to test it. The evaluation findings demonstrated that the SVM model could classify sentiment with a 90% accuracy level. This result was confirmed using an accuracy, precision, recall, and F-measure metrics confusion matrix. The sentiment analysis's findings revealed that most students had a favorable opinion of the library's services, particularly when it came to the staff's effectiveness and the facilities' cleanliness. But there are still certain areas that require work, including managing noise and adding more pertinent book selections. To increase overall library user happiness, it is advised to put in place a program that focuses on enhancing the quality of a quieter learning environment and providing a selection of books that meet the needs of students