A Novel Framework for Malpractice Detection in Online Proctoring

ABSTRACT

Online exams have become increasingly popular in recent years for assessing students' content knowledge, especially during the COVID-19 outbreak. Proctoring for online tests is, however, challenging due to the lack of a face-to-face connection. Furthermore, according to a prior study, online assessments are more vulnerable to various types of cheating, putting their validity at risk. Suspicious student head and mouse movements are identified and depicted in three degrees of detail, allowing course instructors and professors to proctor online tests in a rapid, fast, and trustworthy manner. Our thorough evaluations, which include usage scenarios, well-designed user research, and expert interviews, indicate that our method is effective and practical. © 2022, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.