Revealing Hidden Impression Topics in Students' Journals Based on Nonnegative Matrix Factorization

Research output: Chapter in Book/Report/Conference proceedingConference contribution

3 Citations (Scopus)

Abstract

Students' reflective writings are useful not only for students themselves but also teachers. It is important for teachers to know which concepts were understood well by students and which concepts were not, to continuously improve their classes. However, it is difficult for teachers to thoroughly read the journals of more than one hundred students. In this paper, we propose a novel method to extract common topics and students' common impressions against them from students' journals. Weekly keywords are discovered from journals by scoring noun words with a measure based on TF-IDF term weighting scheme, and then we analyze co-occurrence relationships between extracted keywords and adjectives. We employs nonnegative matrix factorization, one of the topic modeling techniques, to discover the hidden impression topics from the co-occurrence relationships. As a case study, we applied our method on students' journals of the course 'Information Science' held in our university. Our experimental results show that conceptual keywords are successfully extracted, and four significant impression topics are identified. We conclude that our analysis method can be used to collectively understand the impressions of students from journal texts.

Original languageEnglish
Title of host publicationProceedings - IEEE 17th International Conference on Advanced Learning Technologies, ICALT 2017
EditorsRonghuai Huang, Radu Vasiu, Kinshuk, Demetrios G Sampson, Nian-Shing Chen, Maiga Chang
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages298-300
Number of pages3
ISBN (Electronic)9781538638705
DOIs
Publication statusPublished - Aug 3 2017
Event17th IEEE International Conference on Advanced Learning Technologies, ICALT 2017 - Timisoara
Duration: Jul 3 2017Jul 7 2017

Publication series

NameProceedings - IEEE 17th International Conference on Advanced Learning Technologies, ICALT 2017

Conference

Conference17th IEEE International Conference on Advanced Learning Technologies, ICALT 2017
CityTimisoara
Period7/3/177/7/17

Fingerprint

Factorization
Students
student
teacher
Information science
weighting
information science
university

All Science Journal Classification (ASJC) codes

  • Computer Networks and Communications
  • Computer Science Applications
  • Education

Cite this

Taniguchi, Y., Suehiro, D., & Ogata, H. (2017). Revealing Hidden Impression Topics in Students' Journals Based on Nonnegative Matrix Factorization. In R. Huang, R. Vasiu, Kinshuk, D. G. Sampson, N-S. Chen, & M. Chang (Eds.), Proceedings - IEEE 17th International Conference on Advanced Learning Technologies, ICALT 2017 (pp. 298-300). [8001786] (Proceedings - IEEE 17th International Conference on Advanced Learning Technologies, ICALT 2017). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICALT.2017.113

Revealing Hidden Impression Topics in Students' Journals Based on Nonnegative Matrix Factorization. / Taniguchi, Yuta; Suehiro, Daiki; Ogata, Hiroaki.

Proceedings - IEEE 17th International Conference on Advanced Learning Technologies, ICALT 2017. ed. / Ronghuai Huang; Radu Vasiu; Kinshuk; Demetrios G Sampson; Nian-Shing Chen; Maiga Chang. Institute of Electrical and Electronics Engineers Inc., 2017. p. 298-300 8001786 (Proceedings - IEEE 17th International Conference on Advanced Learning Technologies, ICALT 2017).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Taniguchi, Y, Suehiro, D & Ogata, H 2017, Revealing Hidden Impression Topics in Students' Journals Based on Nonnegative Matrix Factorization. in R Huang, R Vasiu, Kinshuk, DG Sampson, N-S Chen & M Chang (eds), Proceedings - IEEE 17th International Conference on Advanced Learning Technologies, ICALT 2017., 8001786, Proceedings - IEEE 17th International Conference on Advanced Learning Technologies, ICALT 2017, Institute of Electrical and Electronics Engineers Inc., pp. 298-300, 17th IEEE International Conference on Advanced Learning Technologies, ICALT 2017, Timisoara, 7/3/17. https://doi.org/10.1109/ICALT.2017.113
Taniguchi Y, Suehiro D, Ogata H. Revealing Hidden Impression Topics in Students' Journals Based on Nonnegative Matrix Factorization. In Huang R, Vasiu R, Kinshuk, Sampson DG, Chen N-S, Chang M, editors, Proceedings - IEEE 17th International Conference on Advanced Learning Technologies, ICALT 2017. Institute of Electrical and Electronics Engineers Inc. 2017. p. 298-300. 8001786. (Proceedings - IEEE 17th International Conference on Advanced Learning Technologies, ICALT 2017). https://doi.org/10.1109/ICALT.2017.113
Taniguchi, Yuta ; Suehiro, Daiki ; Ogata, Hiroaki. / Revealing Hidden Impression Topics in Students' Journals Based on Nonnegative Matrix Factorization. Proceedings - IEEE 17th International Conference on Advanced Learning Technologies, ICALT 2017. editor / Ronghuai Huang ; Radu Vasiu ; Kinshuk ; Demetrios G Sampson ; Nian-Shing Chen ; Maiga Chang. Institute of Electrical and Electronics Engineers Inc., 2017. pp. 298-300 (Proceedings - IEEE 17th International Conference on Advanced Learning Technologies, ICALT 2017).
@inproceedings{518957d3f22743a69982070643ab8803,
title = "Revealing Hidden Impression Topics in Students' Journals Based on Nonnegative Matrix Factorization",
abstract = "Students' reflective writings are useful not only for students themselves but also teachers. It is important for teachers to know which concepts were understood well by students and which concepts were not, to continuously improve their classes. However, it is difficult for teachers to thoroughly read the journals of more than one hundred students. In this paper, we propose a novel method to extract common topics and students' common impressions against them from students' journals. Weekly keywords are discovered from journals by scoring noun words with a measure based on TF-IDF term weighting scheme, and then we analyze co-occurrence relationships between extracted keywords and adjectives. We employs nonnegative matrix factorization, one of the topic modeling techniques, to discover the hidden impression topics from the co-occurrence relationships. As a case study, we applied our method on students' journals of the course 'Information Science' held in our university. Our experimental results show that conceptual keywords are successfully extracted, and four significant impression topics are identified. We conclude that our analysis method can be used to collectively understand the impressions of students from journal texts.",
author = "Yuta Taniguchi and Daiki Suehiro and Hiroaki Ogata",
year = "2017",
month = "8",
day = "3",
doi = "10.1109/ICALT.2017.113",
language = "English",
series = "Proceedings - IEEE 17th International Conference on Advanced Learning Technologies, ICALT 2017",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
pages = "298--300",
editor = "Ronghuai Huang and Radu Vasiu and Kinshuk and Sampson, {Demetrios G} and Nian-Shing Chen and Maiga Chang",
booktitle = "Proceedings - IEEE 17th International Conference on Advanced Learning Technologies, ICALT 2017",
address = "United States",

}

TY - GEN

T1 - Revealing Hidden Impression Topics in Students' Journals Based on Nonnegative Matrix Factorization

AU - Taniguchi, Yuta

AU - Suehiro, Daiki

AU - Ogata, Hiroaki

PY - 2017/8/3

Y1 - 2017/8/3

N2 - Students' reflective writings are useful not only for students themselves but also teachers. It is important for teachers to know which concepts were understood well by students and which concepts were not, to continuously improve their classes. However, it is difficult for teachers to thoroughly read the journals of more than one hundred students. In this paper, we propose a novel method to extract common topics and students' common impressions against them from students' journals. Weekly keywords are discovered from journals by scoring noun words with a measure based on TF-IDF term weighting scheme, and then we analyze co-occurrence relationships between extracted keywords and adjectives. We employs nonnegative matrix factorization, one of the topic modeling techniques, to discover the hidden impression topics from the co-occurrence relationships. As a case study, we applied our method on students' journals of the course 'Information Science' held in our university. Our experimental results show that conceptual keywords are successfully extracted, and four significant impression topics are identified. We conclude that our analysis method can be used to collectively understand the impressions of students from journal texts.

AB - Students' reflective writings are useful not only for students themselves but also teachers. It is important for teachers to know which concepts were understood well by students and which concepts were not, to continuously improve their classes. However, it is difficult for teachers to thoroughly read the journals of more than one hundred students. In this paper, we propose a novel method to extract common topics and students' common impressions against them from students' journals. Weekly keywords are discovered from journals by scoring noun words with a measure based on TF-IDF term weighting scheme, and then we analyze co-occurrence relationships between extracted keywords and adjectives. We employs nonnegative matrix factorization, one of the topic modeling techniques, to discover the hidden impression topics from the co-occurrence relationships. As a case study, we applied our method on students' journals of the course 'Information Science' held in our university. Our experimental results show that conceptual keywords are successfully extracted, and four significant impression topics are identified. We conclude that our analysis method can be used to collectively understand the impressions of students from journal texts.

UR - http://www.scopus.com/inward/record.url?scp=85030260591&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85030260591&partnerID=8YFLogxK

U2 - 10.1109/ICALT.2017.113

DO - 10.1109/ICALT.2017.113

M3 - Conference contribution

T3 - Proceedings - IEEE 17th International Conference on Advanced Learning Technologies, ICALT 2017

SP - 298

EP - 300

BT - Proceedings - IEEE 17th International Conference on Advanced Learning Technologies, ICALT 2017

A2 - Huang, Ronghuai

A2 - Vasiu, Radu

A2 - Kinshuk, null

A2 - Sampson, Demetrios G

A2 - Chen, Nian-Shing

A2 - Chang, Maiga

PB - Institute of Electrical and Electronics Engineers Inc.

ER -