Modeling MOOC student behavior with two-layer hidden Markov models

Chase Geigle, Cheng Xiang Zhai

Research output: Contribution to conferencePaper

Abstract

Massive open online courses (MOOCs) provide educators with an abundance of data describing how students interact with the platform, but this data is highly underutilized today. This is in part due to the lack of sophisticated tools to provide interpretable and actionable summaries of huge amounts of MOOC activity present in log data. To address this problem, we propose a student behavior representation method alongside a method for automatically discovering those student behavior patterns by leveraging the click log data that can be obtained from the MOOC platform itself. Specifically, we propose the use of a two-layer hidden Markov model (2L-HMM) to extract our desired behavior representation, and show that patterns extracted by such a 2L-HMM are interpretable, meaningful, and unique. We demonstrate that features extracted from a trained 2L-HMM can be shown to correlate with educational outcomes.

Original languageEnglish (US)
Number of pages1
StatePublished - Jan 1 2017
Event10th International Conference on Educational Data Mining, EDM 2017 - Wuhan, China
Duration: Jun 25 2017Jun 28 2017

Conference

Conference10th International Conference on Educational Data Mining, EDM 2017
CountryChina
CityWuhan
Period6/25/176/28/17

ASJC Scopus subject areas

  • Computer Science Applications
  • Information Systems

Fingerprint Dive into the research topics of 'Modeling MOOC student behavior with two-layer hidden Markov models'. Together they form a unique fingerprint.

  • Cite this

    Geigle, C., & Zhai, C. X. (2017). Modeling MOOC student behavior with two-layer hidden Markov models. Paper presented at 10th International Conference on Educational Data Mining, EDM 2017, Wuhan, China.