Retrieval Information Using Generalized Vector Space Models And Sentiment Analysis Using Naïve Bayes Classifier For Evaluation Of Lecturers By Students

Abstract

The presence of retrieval information and sentiment analysis may quicken the evaluation of the lecturers and the result of an ongoing issue during the course can be known directly and accurately. This evaluation is conducted every semester by completing the questionnaire. The results of the sentiment analysis are used as the evaluation for lecturer teaching improvement based on the required search results. Currently, the lecturer's assessment is still done manually (with hardcopy) by the LPMI department. Information retrieval is the process of taking users' search requests (queries) according to the likelihood of relevance to the input query. The generalized Vector Space Model (GVSM) uses vector space concepts in determining the relevance of the user input (query) to the document set. Sentiment analysis is the process of document classification. In this research, the sentiment analysis was divided into positive, negative, and neutral classes using the Naive Bayes Classifier (NBC) method. The classification process begins by dividing the document into training data and test data. The search results using the 43 most commented on lecturers rated with 5 keywords using the GVSM had a precision rate of 100% and the recall of 100%, while NBC's sentiment analysis had a precision or truth rate of 72% and an error rate of 28% with a long time of searching and sentiment analysis averaged 21.8 seconds. Based on that data, it can be concluded that the search and sentiment analysis applications can run properly and appropriately.