Digital Signal Processing and Artificial Intelligence for Automatic Learning Jennifer Landes , Sonja Köppl and Meike Klettke 3 4 2024 https://doi.org/10.6025/dspaial/2024/3/4/135-146 https://www.dline.info/dspai/fulltext/v3n4/dspaiv3n4_3.pdf Academic honesty in higher education can be affected by personal or organizational factors. Engaging in dishonest practices diminishes the integrity of the educational setting and can lead to adverse outcomes for individual learners and the academic community. To investigate the elements that contribute to students’ cheating behaviors, a quantitative research study was undertaken, concentrating on the types of assessments and tasks that are most vulnerable to cheating. The data gathered has been analyzed using Machine Learning techniques, and the findings have been presented visually. This research is part of a dissertation project, and the survey outcomes will be utilized for a study involving eye-tracking to assess students’ cheating behaviors. The long-term objective is to create online examination methods resistant to specific cheating tactics.