No full-text available
To read the full-text of this research,
you can request a copy directly from the authors.
Identifying potential cheaters by tracking their behaviors through mouse activities
Abstract
Academic cheating is a significantly common occurrence at the university level in developing countries particularly, in Afghanistan. In online education practices, it could be a difficult task for a better process of secret reconstruction and identifying/ detecting the potential cheaters. Due to a huge number of students and the rapid increase of online education and penetration of the internet (the diversity of electronic devices used by learners in online activities), a big gap exists across creating an honest culture and teacher practices in the classroom. As such, raising the way of early prediction of potential cheaters through the mouse-tracking technique should be an urgent priority. In this paper, the authors examine the developed mouse tracking application along with the developed Moodle plugin in a blended course mid-term (20%) examination for the purpose of detecting and identifying the potential cheaters. The proposed model correctly predicted 94% of students committing illicit actions during the online mid-term examination, which can be possible to early intervene and prevent illegal actions. The study outcome can be used to analyze the learners’ mouse tracking behaviors that lead to a better process of secret reconstruction and transparent space.
... Other studies have focused on individual characteristics, such as students' demographic and personality traits [28,29]. An example of such research is a study by Ref. [30], showing that male students enrolled in hybrid courses are more likely to act dishonestly than female students. ...
... Occasionally, though, these academic standards are violated due to academic misconduct. The problem of academic dishonesty is not confined to traditional learning environments (conventional instruction on campus) but is also prevalent in non-traditional classroom settings, such as the hybrid, blended, and HyFlex formats [19,30,58]. Although choosing the mode of attendance can be a positive and motivating force for students, it can also lead to faulty outcomes in some cases [59], including: Seeking out bugs and loopholes in submission systems and exploiting them, taking advantage of the instructor, or engaging in contract cheating [19,60]. ...
... Nevertheless, it is erroneous to assume that external influences (i.e., the learning environment and academic discipline) alone are responsible for the deterioration of academic integrity, as students' personal characteristics also play an important role [33]. A prior study examining cheating in a non-traditional computer science course found gender differences in the likelihood of engaging in academic dishonesty [30]. Evidence also suggests that certain personality traits might be counterproductive in highly scientifically structured courses [62]. ...
This study analyzed how students' personality traits and course attendance preferences impact academic integrity in the HyFlex learning environment. 535 undergraduate students were given a choice among courses face-to-face (F2F), online, or a hybrid combination of both. The Big Five Inventory and the Academic Integrity Inventory were administered through online questionnaires to STEM students. The findings show that emotional stability and agreeableness positively relate to academic integrity irrespective of attendance mode. So do conscientiousness and agreeableness in the hybrid environment. Conversely, the primarily F2F attendance mode and the personality trait of extraversion are tied to markedly low levels of academic integrity. We conclude that unveiling students' personality traits associated with ethical behaviour would be beneficial when designing HyFlex courses in different learning environments, whether human (F2F), machine-made (online) or a combination of both (hybrid). This, in turn, contributes to better higher quality education and enhances academic integrity.
... Students' goal orientations are strongly associated with the effectiveness of their study habits (Niemivirta et al., 2004;Schwartz et al., 2016). One study from our review used learning analytics to find that distracted study habits (opening and closing multiple tabs while using course learning content) were a predictor of cheating (Sokout et al., 2020). Griebeler (Griebeler, 2019) showed mathematically that students who expect to honestly earn a high exam score experience a high opportunity cost for cheating, and therefore a low incentive to cheat. ...
Scientific and technological advancements over the last three decades have failed to reduce the widespread prevalence of academic dishonesty in higher education, in large part because institutional barriers prevent faculty from adopting existing tools to curb cheating. We conducted a systematic literature review of research on cheating and found that the majority of studies propose new tools without advancing theory or even utilizing existing theory. Although some studies note the systemic nature of academic misconduct, the academic integrity literature requires a robust theoretical framework to model its systemic nature and derive practical strategies. Building on theory from several domains, we propose a systemic model of academic (mis)conduct which predicts group-level effects on students and offers practical guidance for faculty overcoming institutional barriers to curb cheating. We leverage game theory for useful models of systemic, group-level phenomena in this context, and we leverage education reform literature for insights on how to support instructors’ adoption of new tools. Our model, the spectrum of academic conduct, identifies trust as a single dimension governing both cheating behaviors and productive learning behaviors. Integrating insights from pedagogy, conflict management, and organizational psychology, we discuss multiple practical strategies to lower students’ opportunity, motivation, and rationalization to cheat.
... From the recent papers published that considered detecting cheating while performing an online exam is the one proposed by Sokout et al. [23]; the author collected the mouse dynamics of students performing an online midterm exam. They used the mouse dynamics and the Moodle plugin to detect cheaters. ...
The COVID-19 pandemic has made the world focus on providing effective and fair online learning systems. As a consequence, this paper proposed a new intelligent, fair assessment of online examinations for virtual and remotely controlled laboratory experiments running through Laboratory Learning Systems. The main idea is to provide students with an environment similar to being physically present in a Laboratory while conducting practical experiments and exams and detecting cheating with high accuracy at a minimal cost. Therefore, an intelligent assessment module is designed to detect cheating students by analyzing their mouse dynamics using Artificial Intelligence. The mouse interaction behavior method was chosen because it does not require any additional resources, such as a camera and eye tribe tracker, to detect cheating. Various AI algorithms, such as KNN, SVC, Random Forest, Logistic Regression, XGBoost, and LightGBM have been used to classify student mouse behavior to detect cheating, and many metrics are used to evaluate their performance. Moreover, experiments have been conducted on students answering online laboratory experimentations while cheating and when answering the exams honestly. Experimental results indicate that the LightGBM AI algorithm achieves the best cheat detection results up to an accuracy of 90%, precision of 88%, and degree of separation of 95%.
The electronic learning (E-Learning) considered as computer assisted learning has been around since the 1960s but its adoption and popularization mainly started after the popularization of the internet and the web. Since its introduction till present days the e-learning rapidly evolved regarding the technology and the e-learning methods/tools used. Having in mind that it has many benefits for the teacher/instructors from one side and the learners on the other, the e-learning found its application in education, business and the military or wherever is needed. The purpose of this paper is to outline, examine and discuss the evolution, the current state and the new trends in e-learning. The research showed that there is abundance of available technology and e-learning tools that foster and support the learning process. It is evident that e-learning is widely used in education and business and it is expected to grow further. On the other hand there is insufficient evidence of the particular effectiveness of the various pedagogical methodologies used for e-learning. Current state in e-learning and prevailing new trends form the foundations for future direction and development of this field for educational and training purposes. These trends include but are not limited to: blended learning, micro learning, gasification, personalized learning, Massive Open Online Courses, etc.
Learning performance is crucial in students’ academic lives because it opens opportunities for future professional development. However, conventional educational practices do not provide all the necessary skills for university instructors and students to succeed in today's educational context. In addition, due to poor information resources, ineffective ICT tool utilization and the teaching methodologies in developing countries, particularly Afghanistan, a large gap exists across curriculum plans and instructor practices. Learning analytics, as a new educational instrument, has made it possible for higher education actors to reshape the educational environment to be more effective and consistent. In this study, we analyzed multiple research approaches and the results of analytics of various learner aspects to address the aforementioned issues. The research methods were predominantly quantitative-cum-qualitative. Real (quantitative) data were collected based on learners’ explicit actions, such as completing assignments and taking exams, and implicit actions, such interacting and posting on discussion forums. Meanwhile, secondary (qualitative) data collection was conducted on-site at Kabul Polytechnic University (KPU); both blended and traditional class samples were included. The results of this study offer insight into various aspects of learners’ behaviors that lead to their success and indicate the best analytical model/s to provide the highest prediction accuracy. Furthermore, the results of this study could help educational organizations adopt learning analytics to conduct early assessments to evaluate the quality of teaching and learning and improve learners’ performance.
Mouse tracking serves as an alternative to eye tracking in measuring the learning process in education because of its affordability. Moreover, mouse tracking does not require extra hardware, as in the case of eye tracking, because it is a feature in personal computers by default. Therefore, it is possible to implement mouse tracking in a massive open scale. However, mouse tracking has only been implemented in a laboratory setting to date, ostensibly because of the associated extremely high running costs. Nonetheless, there is no available data to support the claim of high resource costs, which has resulted in much speculation among implementers. In general, the implementation of mouse tracking in a non-laboratory environment is still rare. Therefore, the authors developed an application to investigate real-time mouse tracking online. It was implemented on the Moodle learning management system and tested on an online quiz session accessed abroad. Additionally, the application can handle tracking on mobile devices. In this work, the main resources that include CPU, network, RAM, and storage costs were measured when mouse tracking was used. These results can serve as a reference for network and server administrators during future implementation of this technique. It was determined that the characteristics of mouse activities were dynamic in that occasional surges and lulls were observed. Additionally, this article also discussed the advantage of real-time and online implementation to regular online implementation and showed that there is a possibility of implementing mouse tracking on a large scale if mouse tracking data are not aggregated and transmitted as a single data package.
We implemented an online anonymous survey targeted to current and former students, where the interviewed indicate whether and to what extent they cheated during written university examinations. We find that 61% of respondents have cheated once or more. Cheaters are more likely to report that their classmates and friends cheated and that in general people can be trusted. Two different cheating styles emerge: ‘social cheaters,’ who self-report that they have violated the rules interacting with others; ‘individualistic’ cheaters, who self-report that they have used prohibited materials. Only social cheaters exhibit higher levels of trust compared to individualistic cheaters.
Online learning has become very popular over the last decade. However , there are still many details that remain unknown about the strategies that students follow while studying online. In this study, we focus on the direction of detecting 'invisible' collaboration ties between students in online learning environments. Specifically, the paper presents a method developed to detect student ties based on temporal proximity of their assignment submissions. The paper reports on findings of a study that made use of the proposed method to investigate the presence of close submitters in two different massive open online courses. The results show that most of the students (i.e., student user accounts) were grouped as couples, though some bigger communities were also detected. The study also compared the population detected by the algorithm with the rest of user accounts and found that close submitters needed a statistically significant lower amount of activity with the platform to achieve a certificate of completion in a MOOC. These results confirm that the detected close submitters were performing some collaboration or even engaged in unethical behaviors, which facilitates their way into a certificate. However, more work is required in the future to specify various strategies adopted by close submitters and possible associations between the user accounts.
Academic dishonesty among high school students has long since transformed into an epidemic that affects nearly every student, compromising not only their intellectual growth but also their moral development. Yet, beyond the occasional hand-wringing in the media, the problem has been largely ignored by teachers, schools, policymakers, and even character educators. To address this notable failure to respond, the authors developed and evaluated a character education program that sought to use the epidemic of academic dishonesty as an opportunity to reduce cheating and promote integrity. The present article describes the core components and central mechanisms of this schoolwide program as well as results from a 3-year mixed methods study of its implementation at 3 high schools in the Northeastern United States. These results and their implications are discussed in detail. The article also outlines suggestions for further program development and research.
This article uses theoretical concepts from self-efficacy theory, goal theory, expectancy value, and intrinsic motivation theory as a way to organize the vast and largely atheoretical literature on academic cheating. Specifically, it draws on 3 particular questions that students encounter when deciding whether to cheat: (a) What is my purpose?, (b) Can I do this task?, and (c) What are the costs associated with cheating? This article reviews both experimental and nonexperimental evidence related to each of these questions and offers suggestions for future research and instructional practices that will lessen the likelihood of cheating.
This article reviews 1 decade of research on cheating in academic institutions. This re-search demonstrates that cheating is prevalent and that some forms of cheating have increased dramatically in the last 30 years. This research also suggests that although both individual and contextual factors influence cheating, contextual factors, such as students' perceptions of peers' behavior, are the most powerful influence. In addition, an institution's academic integrity programs and policies, such as honor codes, can have a significant influence on students' behavior. Finally, we offer suggestions for managing cheating from students' and faculty members' perspectives. For the last decade, both collectively and individually, we have studied questions of organizational values and ethics. Although the initial point of departure for each of us was ethics in business organizations, we have expended considerable time trying ETHICS & BEHAVIOR, 11(3), 219–232 Copyright © 2001, Lawrence Erlbaum Associates, Inc. Requests for reprints should be sent to Donald L. McCabe, Faculty of Management, Rutgers Univer-sity, Newark, NJ 07102–3027.
In this study, the authors use data from two online courses in principles of economics to estimate a model that predicts exam scores from independent variables of student characteristics. In one course, the final exam was proctored, and in the other course, the final exam was not proctored. In both courses, the first three exams were unproctored. If no cheating took place, the authors expected the prediction model to have the same explanatory power for all exams, and, conversely, if cheating occurred in the unproctored exam, the explanatory power would be lower. Their findings are that both across and within class, variations in the R-squared statistic suggest that cheating was taking place when the exams were not proctored.
E-learning has become an increasingly important learning and teaching mode in recent decades and has been recognized as an efficient and effective learning method. The rapidly rising number of Internet users with smartphones and tablets around the world has supported the spread of e-learning, not only in higher education and vocational training but also in primary and secondary schools.
E-learning and traditional distance education approaches share the emphasis on “any time, any place” learning and the assumption that students are at a distance from the instructor. The design of the initial e-learning courses tended to replicate existing distance education practice based on content delivery. However, long textual lectures were clearly not suitable for the online environment. These early insights guided the development of e-learning (technical and pedagogical) and emphasized the need for communication and interaction.
E-learning describes learning delivered fully online where technology mediates the learning process, teaching is delivered entirely via Internet, and students and instructors are not required to be available at the same time and place.
E-learning practices are evolving with the mutual influence of technological e-learning platforms and pedagogical models. Today, the broad penetration and consolidation of e-learning needs to advance and open up to support new possibilities. Future e-learning should encompass the use of Internet technologies for both formal and informal learning by leveraging different services and applications.
The purpose of this chapter is to provide a general analysis of the evolution and future trends in e-learning. The authors intend to summarize findings from contemporary research into e-learning in order to understand its current state and to identify the main challenges in the technological and pedagogical affordances of e-learning.
In a (t, n) secret sharing scheme, a secret s is divided into n shares and shared among a set of n shareholders by a mutually trusted dealer in such a way that any t or more than t shares will be able to reconstruct this secret; but fewer than t shares cannot know any information about the secret. When shareholders present their shares in the secret reconstruction
phase, dishonest shareholder(s) (i.e. cheater(s)) can always exclusively derive the secret by presenting faked share(s) and
thus the other honest shareholders get nothing but a faked secret. Cheater detection and identification are very important
to achieve fair reconstruction of a secret. In this paper, we consider the situation that there are more than t shareholders participated in the secret reconstruction. Since there are more than t shares (i.e. it only requires t shares) for reconstructing the secret, the redundant shares can be used for cheater detection and identification. Our proposed
scheme uses the shares generated by the dealer to reconstruct the secret and, at the same time, to detect and identify cheaters.
We have included discussion on three attacks of cheaters and bounds of detectability and identifiability of our proposed scheme
under these three attacks. Our proposed scheme is an extension of Shamir’s secret sharing scheme.
In this paper we analyze the cheating detection and cheater identification problems for the secret sharing schemes based on the Chinese remainder theorem (CRT), more exactly for Mignotte (1) and Asmuth-Bloom (2) schemes. We prove that the majority of the solutions for Shamir's scheme (3) can be translated to these schemes and, moreover, there are some interesting specific solutions. I. INTRODUCTION
The log of all interactions the student makes with an online homework tutor (MasteringPhysics), including start time, finish time, correct answers, wrong answers, and hints requested allowed the development of an algorithm which assigns a "copying" probability to each problem completed. This algorithm was applied to three successive Newtonian Mechanics classes at MIT: Fall 2003, Fall 2004, and Fall 2005, affording unique insight into the dynamics of physics homework copying, and allowing contrasts between the performance and behavioral patterns of students who copy a lot and students who copy a little or copy none at all. Observations show that repetitive homework copying is correlated with steeply declining exam performance, and that repetitive copiers are four times more likely to fail to complete the - required two semester physics sequence on time than students who don't copy. Observations of several behavioral patterns associated with repetitive homework copying are reported - these patterns, combined with data from a self-reported cheating survey of MIT freshman, shed new light on the reasons students copy and steps educators can take to reduce homework copying. (cont.) Through the implementation of several of these steps, we observe that between Fall 2003 and Fall 2005 detected homework copying dropped by -40%. Although efforts to reduce homework copying may not be an innovation in teaching, our study indicates it may be the best path to increasing student learning and success. Thesis (S.M.)--Massachusetts Institute of Technology, Dept. of Physics, 2006. Includes bibliographical references (p. 131-141).
How to Stop Cheating in College
- barthel
M. BARTHEL, "How to Stop Cheating in College", The Atlantic, 2016.
Academic Cheating Statistics Say There’s Lots of Work to Do
- Unicheck
Academic Integrity: A Critical Challenge for Schools
- D Wangaard
- J Stephens
D. Wangaard and J. Stephens, "Academic Integrity: A Critical
Challenge for Schools", 2011.
Academic Environment Can Affect Student Honesty
- maloshonok
N. Maloshonok, "Academic Environment Can Affect Student
Honesty", Научно-образовательный портал IQ, 2020. [Online].
Available: https://iq.hse.ru/en/news/194822895.html. [Accessed: 30-May-2020].
Support Vector Machine — Introduction to Machine Learning Algorithms
- gandhi
R. Gandhi, "Support Vector Machine -Introduction to Machine
Learning Algorithms", Medium, 2018. [Online]. Available:
https://towardsdatascience.com/support-vector-machine-introductionto-machine-learning-algorithms-934a444fca47. [Accessed: 09-Jun-2020].
A Data-driven Method for the Detection of Close Submitters in Online Learning Environments
- J Ruipérez-Valiente
- S Joksimoviü
- V Kovanoviü
- D Gaševiü
- P Muñoz-Merino
- C Delgado Kloos
Survey Shows Cheating and Academic Dishonesty Prevalent in Colleges and Universities
- Kessler International
Kessler International, "Survey Shows Cheating and Academic
Dishonesty Prevalent in Colleges and Universities", 2017.
The Interrelationship of Cheating, IQ, Grades, Family Socioeconomic Level, and Teacher Rating of High School Students
- leveque
K. Leveque, "The Interrelationship of Cheating, IQ, Grades, Family
Socioeconomic Level, and Teacher Rating of High School Students",
Master's Theses, Loyola University Chicago, 1966.
Simple Tutorial on SVM and Parameter Tuning in Python and R | HackerEarth Blog
- jain
R. Jain, "Simple Tutorial on SVM and Parameter Tuning in Python and
R | HackerEarth Blog", HackerEarth Blog, 2017. [Online]. Available:
https://www.hackerearth.com/blog/developers/simple-tutorial-svmparameter-tuning-python-r/. [Accessed: 16-Sep-2020].
6 Available Models | The caret Package
- kuhn
M. Kuhn, "6 Available Models | The caret Package", Topepo.github.io,
2020. [Online]. Available: https://topepo.github.io/caret/availablemodels.html. [Accessed: 16-Sep-2020].
Implementation of real-time online mouse tracking on overseas quiz session
- F Purnama
- O Sukhbaatar
- L Choimaa
- T Usagawa
F. Purnama, O. Sukhbaatar, L. Choimaa and T. Usagawa,
"Implementation of real-time online mouse tracking on overseas quiz
session", Education and Information Technologies, 2020. Available:
10.1007/s10639-020-10141-3 [Accessed 10 June 2020].
Academic Cheating Statistics Say There's Lots of Work to Do
- Unicheck
Unicheck, "Academic Cheating Statistics Say There's Lots of Work to
Do", 2019.
Professors Use Technology to Fight Student Cheating
US News and World Report, "Professors Use Technology to Fight
Student Cheating", US, 2020.
Chapter 2: SVM (Support Vector Machine) — Theory
- patel