Who’s Cheating?: Mining Patterns of Collusion from Text and Events in Online Exams

Catherine Cleophas; Christoph Hönnige; Frank Meisel; Philipp Meyer

doi:10.1287/ited.2021.0260

Who’s Cheating? Mining Patterns of Collusion from Text and Events in Online Exams

Catherine Cleophas^*, Christoph Hönnige, Frank Meisel, Philipp Meyer

^*Corresponding author for this work

Institute of Political Science

Kiel University

Research output: Contribution to journal › Article › Research › peer review

Abstract

As the COVID-19 pandemic motivated a shift to virtual teaching, exams have increasingly moved online too. Detecting cheating through collusion is not easy when tech-savvy students take online exams at home and on their own devices. Such online at-home exams may tempt students to collude and share materials and answers. However, online exams’ digital output also enables computer-aided detection of collusion patterns. This paper presents two simple data-driven techniques to analyze exam event logs and essay-form answers. Based on examples from exams in social sciences, we show that such analyses can reveal patterns of student collusion. We suggest using these patterns to quantify the degree of collusion. Finally, we summarize a set of lessons learned about designing and analyzing online exams.

Original language	English
Article number	57-135
Pages (from-to)	84-94
Number of pages	11
Journal	INFORMS Transactions on Education
Volume	23
Issue number	2
DOIs	https://doi.org/10.1287/ited.2021.0260
Publication status	Published - 1 Oct 2021

Keywords

learning analytics
event mining
text mining
online assessment

ASJC Scopus subject areas

Education
Management Information Systems
Management Science and Operations Research

Access to Document

10.1287/ited.2021.0260Licence: CC BY 4.0

Cite this

@article{2002bc35b6934772b5dd97f78ace55dc,

title = "Who{\textquoteright}s Cheating?: Mining Patterns of Collusion from Text and Events in Online Exams",

abstract = "As the COVID-19 pandemic motivated a shift to virtual teaching, exams have increasingly moved online too. Detecting cheating through collusion is not easy when tech-savvy students take online exams at home and on their own devices. Such online at-home exams may tempt students to collude and share materials and answers. However, online exams{\textquoteright} digital output also enables computer-aided detection of collusion patterns. This paper presents two simple data-driven techniques to analyze exam event logs and essay-form answers. Based on examples from exams in social sciences, we show that such analyses can reveal patterns of student collusion. We suggest using these patterns to quantify the degree of collusion. Finally, we summarize a set of lessons learned about designing and analyzing online exams.",

keywords = "learning analytics, event mining, text mining, online assessment",

author = "Catherine Cleophas and Christoph H{\"o}nnige and Frank Meisel and Philipp Meyer",

year = "2021",

month = oct,

day = "1",

doi = "10.1287/ited.2021.0260",

language = "English",

volume = "23",

pages = "84--94",

journal = "INFORMS Transactions on Education",

issn = "1532-0545",

publisher = "INFORMS Institute for Operations Research and the Management Sciences",

number = "2",

}

TY - JOUR

T1 - Who’s Cheating?

T2 - Mining Patterns of Collusion from Text and Events in Online Exams

AU - Cleophas, Catherine

AU - Hönnige, Christoph

AU - Meisel, Frank

AU - Meyer, Philipp

PY - 2021/10/1

Y1 - 2021/10/1

N2 - As the COVID-19 pandemic motivated a shift to virtual teaching, exams have increasingly moved online too. Detecting cheating through collusion is not easy when tech-savvy students take online exams at home and on their own devices. Such online at-home exams may tempt students to collude and share materials and answers. However, online exams’ digital output also enables computer-aided detection of collusion patterns. This paper presents two simple data-driven techniques to analyze exam event logs and essay-form answers. Based on examples from exams in social sciences, we show that such analyses can reveal patterns of student collusion. We suggest using these patterns to quantify the degree of collusion. Finally, we summarize a set of lessons learned about designing and analyzing online exams.

AB - As the COVID-19 pandemic motivated a shift to virtual teaching, exams have increasingly moved online too. Detecting cheating through collusion is not easy when tech-savvy students take online exams at home and on their own devices. Such online at-home exams may tempt students to collude and share materials and answers. However, online exams’ digital output also enables computer-aided detection of collusion patterns. This paper presents two simple data-driven techniques to analyze exam event logs and essay-form answers. Based on examples from exams in social sciences, we show that such analyses can reveal patterns of student collusion. We suggest using these patterns to quantify the degree of collusion. Finally, we summarize a set of lessons learned about designing and analyzing online exams.

KW - learning analytics

KW - event mining

KW - text mining

KW - online assessment

UR - http://www.scopus.com/inward/record.url?scp=85154534946&partnerID=8YFLogxK

U2 - 10.1287/ited.2021.0260

DO - 10.1287/ited.2021.0260

M3 - Article

SN - 1532-0545

VL - 23

SP - 84

EP - 94

JO - INFORMS Transactions on Education

JF - INFORMS Transactions on Education

IS - 2

M1 - 57-135

ER -