A Part-of-Speech-Based Exploratory Text Mining of Students’ Looking-Back Evaluation

Abstract

In our lectures at universities, we observe that the students’ attitudes affects a lot to their achievements. In order to prove this observation based on data, we have been investigating to find effective methods that extract students’ attitudes from lecture data; such as examination score as an index to student’s achievement, attendance and homework data for his/her effort, and answer texts of the term-end questionnaire as information source of attitude. In this chapter, we take another approach to investigate the influences of words used in the answer texts of students on their achievements. We use a machine learning method called Support Vector Machine (SVM), which is a tool to create a model for classifying the given data into two groups by positive and negative training sample data. We apply SVM to the answer texts for analyzing the influences of parts of speech of words to the student’s achievement. Even though adjectives and adverbs are the same in the sense that they modify nouns and verbs, we found that adverbs affects much more than adjectives, as a result. From our experiences so far, we believe that analysis of answers to the evaluations of students toward themselves and lectures are very useful source of finding the students’ attitudes to learning.