Exploring machine learning methods to automatically identify students in need of assistance

Alireza Ahadi, Raymond Lister, Heikki Haapala, Arto Vihavainen

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

71 Citations (Scopus)

Abstract

Methods for automatically identifying students in need of assistance have been studied for decades. Initially, the work was based on somewhat static factors such as students' educational background and results from various questionnaires, while more recently, constantly accumulating data such as progress with course assignments and behavior in lectures has gained attention. We contribute to this work with results on early detection of students in need of assistance, and provide a starting point for using machine learning techniques on naturally accumulating programming process data. When combining source code snapshot data that is recorded from students' programming process with machine learning methods, we are able to detect high- and low-performing students with high accuracy already after the very first week of an introductory programming course. Comparison of our results to the prominent methods for predicting students' performance using source code snapshot data is also provided. This early information on students' performance is beneficial from multiple viewpoints. Instructors can target their guidance to struggling students early on, and provide more challenging assignments for high-performing students. Moreover, students that perform poorly in the introductory programming course, but who nevertheless pass, can be monitored more closely in their future studies.

Original languageEnglish
Title of host publicationICER 2015
Subtitle of host publicationProceedings of the 2015 ACM Conference on International Computing Education Research
Place of PublicationNew York, NY
PublisherAssociation for Computing Machinery, Inc
Pages121-130
Number of pages10
ISBN (Electronic)9781450336284
ISBN (Print)9781450336307
DOIs
Publication statusPublished - 2015
Externally publishedYes
EventAnnual ACM Conference on International Computing Education Research (11th : 2015) - Omaha, United States
Duration: 9 Aug 201513 Aug 2015

Conference

ConferenceAnnual ACM Conference on International Computing Education Research (11th : 2015)
Abbreviated titleICER 2015
CountryUnited States
CityOmaha
Period9/08/1513/08/15

Keywords

  • introductory programming
  • source code snapshot analysis
  • programming behavior
  • educational data mining
  • learning analytics
  • novice programmers
  • detecting students in need of assistance

Fingerprint Dive into the research topics of 'Exploring machine learning methods to automatically identify students in need of assistance'. Together they form a unique fingerprint.

Cite this