Detection and Evaluation of Cheating on College Exams using Supervised Classification

Cavalcanti, Elmano Ramalho; Pires, Carlos Eduardo Santos; Cavalcanti, Elmano Pontes; Pires, Vládia Freire

doi:10.15388/infedu.2012.09

Cited by 19 publications

(6 citation statements)

References 29 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…are important to develop a holistic culture of integrity, the other part of that equation is detection and penalty. Detection especially plays a significant role in helping to pave the way for learning opportunities that can also lead to rehabilitation and restoration of the alleged students (Perkins, Gezgin, and Roe, 2020;Cavalcanti et al 2012). Therefore, we focus on the detection data of the University across 2018-2020 to track the effectiveness of the COVID19 response by the University below as evidence.…”

Section: Resultsmentioning

confidence: 99%

“…While the University does not claim that their efforts have ensured they had no misconducts, authors posit that indeed the efforts by the University supported the faculty and they felt safe and encouraged to become vigilant and use the academic integrity online system to both detect and report allegations. The percentage changes in the number of cases of allegations reported also point to the fact that the training, workshops, information, videos, and the general culture of the University that was already pre-existent, helped detect and report such cases, thus perhaps acting as further deterrent to the actual misconduct behaviours (Cavalcanti et al 2012 ).…”

Section: Discussionmentioning

confidence: 99%

See 1 more Smart Citation

Culture of integrity – institutional response to integrity during COVID19

2022

View full text Add to dashboard Cite

COVID19 forced most education institutions to move their education provisions to digital platforms almost overnight to ensure continued learning for students. Variable factors relating to educational technologies, ease of use, accessibility and funding meant the process was more challenging for some than others. However even the most agile and well-prepared educational institutions faced a hurdle during remote learning when it came to integrity in assessing students online.This article tracks the efforts by one western university in a Middle Eastern country, tracing back the systemic changes, evolution of policies and procedures that culminated into a campus-wide response that helped redesign assessments, increased awareness among faculty towards recognising and reporting cases, and the implementation of integrity pledges. It is believed this article presents a well-rounded case study as a good practice guide for other tertiary institutions on the importance of building a culture of integrity prior to any crisis, that can help whether such situations need to arrive in the future.

show abstract

Section: Resultsmentioning

confidence: 99%

Section: Discussionmentioning

confidence: 99%

Culture of integrity – institutional response to integrity during COVID19

2022

View full text Add to dashboard Cite

show abstract

“…In recent years, different machine learning methods have been explored for cheating detection (e.g., Cavalcanti et al, 2012;Hao & Li, 2022;Kim et al 2016;Liao et al, 2021;Man et al 2019;Pan & Wollack, 2021, 2022Thomas, 2016;Tiong & Lee, 2021;Zhou & Jiao, 2022a, b;Zopluoglu, 2019). These include both supervised and unsupervised machine learning algorithms such as decision trees, discriminant analysis, logistic regression, gradient boosting, support vector machine (SVM), random forest, and stacking ensemble learning algorithms as well as deep learning algorithms such as long short-term memory (LSTM; Tang et al, 2023).…”

Section: Introductionmentioning

confidence: 99%

Integrating Psychometric Analysis and Machine Learning to Augment Data for Cheating Detection in Large-Scale Assessment

Hong¹,

Yadav²,

Li³

2023

Preprint

View full text Add to dashboard Cite

Machine learning methods have been explored for cheating detection in large-scale assessment programs. While some studies analyzed item response and response time (RT) data, a few studies experimented with other data and data augmentation in cheating detection. However, none study has explored data augmentation integrating results from both psychometric analysis and machine learning for cheating detection though Kim et al. (2016) compared the results from these two perspectives. This study explored data augmentation in the stacking learning for cheating detection adding both person-fit measures from psychometric analysis and outlier measures from anomaly detection methods. An empirical data set from a high-stake large-scale testing program is used to demonstrate the application of the proposed method. Class imbalance is addressed via resampling. The performance of the proposed method is compared with alternative approaches. It is found the proposed data augmentation approach effectively increases the cheating detection accuracy with the highest F1 score compared with the values reported in similar studies.

show abstract

“…The prevention of cheating during unproctored online exams has gained significant attention [3]. Academic dishonesty is unethical, and exam cheating is more dangerous than other forms [2], [4]- [8], [9]. Online education will continue to expand, posing new obstacles.…”

Section: Introductionmentioning

confidence: 99%

Proctoring and Non-proctoring Systems

Baso¹

2022

IJACSA

View full text Add to dashboard Cite

This research describes learning achievement assessment technology, especially proctor technology. This study compares and contrasts proctoring and non-proctoring procedures used for online exams. The sample case used was the test scores of students enrolled in Hasanuddin University's Indonesian Arabic translation course. The research method used was a non-experimental quantitative method that compared students' online test results using proctoring and non-proctoring systems during online exams. The test scores of 101 students (40 male and 61 female students) from two different classes were sampled. The results of the tests for both classes were collected six times: three times using the proctoring method and three times using the non-proctoring system. A trend analysis was performed on the data. SPSS 26 was used to analyze the data via the two-way ANOVA procedure. The results indicate that the online proctoring system resulted in lower test scores than the online non-proctoring system, while the variables of class and gender did not affect the learning results.

show abstract

Detection and Evaluation of Cheating on College Exams using Supervised Classification

Cited by 19 publications

References 29 publications

Culture of integrity – institutional response to integrity during COVID19

Culture of integrity – institutional response to integrity during COVID19

Integrating Psychometric Analysis and Machine Learning to Augment Data for Cheating Detection in Large-Scale Assessment

Proctoring and Non-proctoring Systems

Contact Info

Product

Resources

About