Knowledge Resource
Research Summary: Early Prediction of AI-Assisted Cheating Risk in Online Exams Through Learning Analytics
- Original authors
- Attribution requires verification
- Original source
- arXiv — Computers and Society
- Summary & Analysis prepared by
- Aziz Shuaib Ausi
- Resource type
- Research Summary / Knowledge Resource
- Resource published on AZIZ OS
- 3 October 2026
- Reading time
- 1 min
- Publication type
- Knowledge Resource
- Availability
- Open access
About this Summary & Analysis
AZIZ OS provides independently prepared summaries and analytical interpretations of externally published research and knowledge sources. The underlying works remain attributable to their original authors and rights holders. This resource is intended to improve accessibility and understanding and does not replace the original publication.
Research from a study involving 52 first-year undergraduates in Turkey indicates that AI-assisted cheating risk in online examinations can be predicted early in the semester. By analyzing students' digital traces within a Learning Management System (LMS) during the initial eight weeks, a significant proportion (44.2%) of students were identified as high-risk for AI-assisted cheating, based on behaviors like copying, focus-loss, and right-click events during proctored online exams.
Why it matters
The ability to predict AI-assisted cheating early in an academic period offers a proactive mechanism to safeguard the integrity of online assessments and the value of credentials. This capability can inform the development of robust educational policies and technological interventions to mitigate risks, ensuring equitable and fair evaluation processes in an increasingly digital learning environment.
Key insights
- AI-assisted cheating presents a significant threat to the integrity of online examinations.
- Early prediction of AI-assisted cheating risk is possible by analyzing student digital traces in an LMS.
- Data from the first eight weeks of a semester can identify students at high risk for AI-assisted cheating in final exams.
- Suspicious behaviors recorded during proctored exams, such as copy events, focus-loss, and right-click events, are indicators of AI-assisted cheating risk.
- A study of 52 undergraduates found 44.2% were labeled high-risk based on these indicators during a final exam.
Source
arXiv — Computers and Society — https://arxiv.org/abs/2609.37280
Related intelligence and resources
Previous
Exploring Causal Mechanisms with Generative Agent-Based Models
Next
Student Perceptions of Tablet-Based Teaching and Learning in TNE Undergraduate Mathematics
The role of context and visual-spatial memory in recall performance within an immersive VR environment
Knowledge Resource
Expanding conceptual evidence-building with the science of learning: integrating evidence weights, alignment estimates and iterative updates for educational innovations
Knowledge Resource
What is a green school? Understanding stewardship, well-being, and sustainability education
Knowledge Resource
From information providers to learning designers: heutagogical teaching practices in AI-enhanced education
Knowledge Resource
From journal validation to quality governance: a policy analysis of India's transition from UGC-CARE to quality-oriented research assessment and its implications for medical and dental education
Knowledge Resource
Exploring primary teachers’ emotional and instructional challenges in supporting students with general reading difficulties in Saudi Arabia
Knowledge Resource
Citation
Cite the original work (APA 7)
The original source is authoritative for this citation. Cite the source publication directly — this attribution is pending verification. Open the original source.
Verification
This is an authenticated AZIZ OS resource record.
- Verification ID
- ASA-EXE-2026-01151
- Version
- v1.0 · r0
- Issued
- 3 October 2026
- Resource prepared by
- Aziz Shuaib Ausi
- Resource status
- Research Summary / Knowledge Resource
- Underlying work
- Early Prediction of AI-Assisted Cheating Risk in Online Exams Through Learning Analytics
- Original authors
- Attribution requires verification
- Original source
- arXiv — Computers and Society
- Provenance status
- Attribution requires verification
- Rights
- Underlying publication rights remain with the respective copyright holder(s). Refer to the original source for authoritative publication and licensing information.
This verification confirms the AZIZ OS resource record and its documented provenance. It does not establish authorship of the underlying external work.