Inferring Students’ Personality from Their Communication Behavior in Web-based Learning Systems

Wen Wu*, Li CHEN, Qingchang Yang, You Li

*Corresponding author for this work

Research output: Contribution to journalJournal articlepeer-review

12 Citations (Scopus)


Communication tools have been popular in web-based learning systems because of their ability to promote the interaction and potentially alleviate the high dropout issue. In recent years, with the increased awareness among researchers about the individual difference of the students, more and more personalized learning supports have been developed. Although personality has been considered as a valuable personal factor being incorporated into the provision of personalized learning, existing studies mainly acquire students’ personality via questionnaires, which unavoidably demands user efforts. In this paper, we are motivated to derive students’ Big-Five personality from their communication behavior in web-based learning systems. Concretely, we first identify a set of features that are significantly influenced by students’ personality, which not only include their communication activities carried out in both synchronous and asynchronous web-based learning environment, but also their linguistic content in conversational texts. We then develop inference model to unify these features for determining students’ five personality traits, and find that students’ usage of different communication tools can be effective in predicting their Big-Five personality.

Original languageEnglish
Pages (from-to)189-216
Number of pages28
JournalInternational Journal of Artificial Intelligence in Education
Issue number2
Publication statusPublished - 15 May 2019

Scopus Subject Areas

  • Education
  • Computational Theory and Mathematics

User-Defined Keywords

  • Linguistic content
  • Personality prediction
  • Synchornous/asynchronous communication
  • User survey
  • Web-based learning system


Dive into the research topics of 'Inferring Students’ Personality from Their Communication Behavior in Web-based Learning Systems'. Together they form a unique fingerprint.

Cite this