Correlation of topic model and student grades using comment data mining

Shaymaa E. Sorour, Kazumasa Goda, Tsunenori Mine

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

7 Citations (Scopus)

Abstract

Assessment of learning progress and learning gain play a pivotal role in education fields. New technologies like comment data mining promote the use of new types of contents; student comments highly reflect student learning attitudes and activities compared to more traditional methods and they can be a powerful source of data for all forms of assessment. A teacher just asks students after every lesson to freely describe and write about their learning situations and behaviors. This paper proposes new methods based on a statistical latent class "Topics" for the task of student grade prediction; our methods convert student comments using latent semantic analysis (LSA) and probabilistic latent semantic analysis (PLSA), and generate prediction models using support vector machine (SVM) and artificial neural network (ANN) to predict student final grades. The experimental results show that our methods can accurately predict student grades based on comment data.

Original languageEnglish
Title of host publicationSIGCSE 2015 - Proceedings of the 46th ACM Technical Symposium on Computer Science Education
EditorsCarl Alphonce, Adrienne Decker, Kurt Eiselt, Jodi Tims
PublisherAssociation for Computing Machinery, Inc
Pages441-446
Number of pages6
ISBN (Electronic)9781450329668
DOIs
Publication statusPublished - Feb 24 2015
Event46th SIGCSE Technical Symposium on Computer Science Education, SIGCSE 2015 - Kansas City, United States
Duration: Mar 4 2015Mar 7 2015

Publication series

NameSIGCSE 2015 - Proceedings of the 46th ACM Technical Symposium on Computer Science Education

Other

Other46th SIGCSE Technical Symposium on Computer Science Education, SIGCSE 2015
CountryUnited States
CityKansas City
Period3/4/153/7/15

All Science Journal Classification (ASJC) codes

  • Education
  • Computer Science (miscellaneous)

Fingerprint Dive into the research topics of 'Correlation of topic model and student grades using comment data mining'. Together they form a unique fingerprint.

  • Cite this

    Sorour, S. E., Goda, K., & Mine, T. (2015). Correlation of topic model and student grades using comment data mining. In C. Alphonce, A. Decker, K. Eiselt, & J. Tims (Eds.), SIGCSE 2015 - Proceedings of the 46th ACM Technical Symposium on Computer Science Education (pp. 441-446). (SIGCSE 2015 - Proceedings of the 46th ACM Technical Symposium on Computer Science Education). Association for Computing Machinery, Inc. https://doi.org/10.1145/2676723.2677259