Maximizing Academic Integrity While Minimizing Stress in the Virtual Classroom

Abstract

The article documents students' experiences with the shift online at the onset of the COVID-19 pandemic and provides informed recommendations to STEM instructors regarding academic integrity and student stress. Over 500 students were surveyed on these topics, including an open-ended question. Students experienced more stress and perceived a greater workload in online courses and therefore preferred in-person courses overall. Personal awareness of cheating during online exams is positively correlated with the proportion of cheating a student perceives. Fear of getting caught is the best cheating deterrent while getting a better grade makes cheating most enticing. Randomization of questions and answer choices is perceived as a highly effective tool to reduce cheating and is reported as the least stress-inducing method. Inability to backtrack and time limits cause students the most stress. Students report that multiple choice questions are the least effective question type to discourage cheating and oral exam questions cause the most stress. Use of camera and lockdown browser or being video- and audio- recorded caused the majority of student stress. Yet, nearly 60% agree that the combination of camera and lockdown browser is an effective deterrent. Recommendations: (i) Be transparent regarding academic dishonesty detection methods and penalties. (ii) Use online invigilating tools. (iii) Synchronize exams and (iv) randomize exam questions. (v) Allow backtracking. (vi) Avoid converting in-person exams to online exams; instead, explore new ways of designing exams for the online environment.

Keywords: academic integrity; cheating; exams; online exams; stress; virtual classroom.

FIG 1

Student’s (N = 502) perceptions of in-person versus virtual courses. Students were asked which modality: they preferred, caused more stress, for which they put forth more effort, had a greater workload, and caused more test anxiety. Asterisks indicate a difference among the three answer choices available to survey respondents (in-person, virtual, no preference) relative to the expected percentages under the null hypothesis (Chi-square Goodness of Fit Tests: P < 0.001 for all tests).

FIG 2

Percent of respondents indicating stress in virtual and in-person courses based on preferred mode of instruction. Asterisks indicate significant differences between observed and expected percentages based on a null hypothesis of no relationship between course modality and perceived stress (Chi-Square Goodness of Fit Tests: P < 0.001).

FIG 3

(A) Respondents’ perception of cheating occurrences during virtual and in-person exams. Overall, students indicated that they perceived that academic dishonesty occurs more frequently during virtual relative to in-person exams (Related-Samples Wilcoxon Signed Rank Test: T = 86321, P < 0.001). (B) 4-year students perceived more peers cheating on virtual exams relative to 2-year peers (Mann-Whitney U: U = 37612, P < 0.001). (C) 2-year and 4-year students perceived similar levels of cheating on in-person exams (Mann-Whitney U: U = 27847.5, P = 0.110).

FIG 4

Percent of respondents indicating they were personally aware of a strategy being used during a virtual exam. Respondents were able to select more than one response.

FIG 5

The number of cheating strategies respondents were personally aware of peers using during virtual exams was positively correlated with the percentage of peers the respondents perceived to be cheating on virtual exams (Spearman’s rank correlation: N = 502, r_s = 0.499, P < 0.001).

FIG 6

Percent of respondents indicating what (A) encourages and (B) discourages students to cheat. Respondents were able to select more than one response.

FIG 7

Percent of respondents agreeing, disagreeing, and neither agreeing nor disagreeing that each of (A) five exam logistics (B) four question types and (C) four technology requirements caused stress during virtual exams. (D) There were differences between the percentage of 2-year and 4-year respondents indicating that various technological requirements caused stress during virtual exams. More 4-year students reported stress related to having cameras on in combination with lockdown browsers and being recorded relative to 2-year peers (Chi-square Tests: P < 0.001). Fewer 4-year students reported stress related to lockdown browsers relative to 2-year peers (Chi-square test: P = 0.002).

FIG 8

Percent of respondents agreeing, disagreeing, and neither agreeing nor disagreeing that each of (A) five exam logistics (B) four question types and (C) four technology requirements were effective at maximizing academic integrity during virtual exams. (D) There were differences between the percentage of 2-year and 4-year respondents indicating that various technological requirements maximized integrity. Four-year students were more likely to indicate that lockdown browsers, cameras in combination with lockdown browsers, and being recorded would maximize integrity relative to 2-year peers (Chi-Square Tests: P = 0.049, P < 0.001, and P = 0.001, respectively).