AUTOMATED SUTDENT FEEDBACK CONTENT ANALYSIS USING STASTICAL METHODS

Keywords

Student feedback, logistic regression, text mining, review analytics.

Abstract

every year massive amount of feedback is gathered from students regarding subjects and its respective faculty. The amount of time to analyze this data manually is a very tedious and time consuming. Pure manual analysis cannot deal with the ever growing scale of data. Automatic summarization is the process of reducing a text document it substantially reduces the costs of analyzing large collections of text using Text mining is concerned with the text analysis of data for finding patterns and regularities in the student feedback data sets. We propose a novel method using multivariate predictive model for conceptual content analytics based on student reviews using standard statistical model inverse regression. Finally the analysis is used in the prediction studies and to illustrate their effectiveness against the learner’s feedback. This will act as a multi-label classifier in order to identify the classification and prediction of student problems and statistically measuring student preferences by analyzing qualitative descriptive gathering reviews.