Home // COGNITIVE 2017, The Ninth International Conference on Advanced Cognitive Technologies and Applications // View article

Estimating Student's Viewpoint to Learning from Lecture/Self-Evaluation Texts

Authors:
Toshiro Minami
Yoko Ohura
Kensuke Baba

Keywords: Text Mining; Text Analysis; Term-usage; Educational Data Mining; Lecture Data Analytics

Abstract:
Our eventual goal is to help students learn more effectively. Toward this goal, we have asked the students to retrospectively evaluate them and the class by looking back what they have learned, and analyzed the answer-texts for capturing them objectively. We found that their viewpoints affect their performances. Students with wider viewpoints get better performances than those with concentrated viewpoints. In this paper, we analyze the answer texts for two contrasting targets; lecture (L) vs. student (S), and good point (G) vs. bad point (B). We propose an index for measuring the term usage and analyze the answer texts using this index. We find that most terms are exclusively used in either one of the contrasting questions. For the numbers of exclusively-used terms, L and G respectively outperform S and B. Thus, students pay more attentions to lectures than themselves and to good points than bad points, as they evaluate. Further, the terms exclusively used in the combination of L-S and G-B, i.e., LG, LB, SG, and SB, show the points of evaluation view of students more specifically.

Pages: 38 to 43

Copyright: Copyright (c) IARIA, 2017

Publication date: February 19, 2017

Published in: conference

ISSN: 2308-4197

ISBN: 978-1-61208-531-9

Location: Athens, Greece

Dates: from February 19, 2017 to February 23, 2017