A Behavioral Biometrics Based and Machine Learning Aided Framework for Academic Integrity in E-Assessment

Abstract

The common approaches to academic integrity in the e-learning environment are resource-intensive and require technology and/or dedicated invigilation staff to monitor assessment activities. These approaches are observational and often external to the learning spaces where the majority of the instructional content resides. Authentic assessments such as discussions, projects and portfolios may not always undergo the same scrutiny as high-stakes examinations and therefore differ in the level of identity and authorship assurance they provide. In this paper, we propose an integrated approach to enhancing academic integrity of e-assessments. The approach is based on behavioral biometrics and aided by machine-learning techniques. It provides continuous identity and authorship assurance throughout the learning activities within the existing learning space. It can be applied to measure the degree of learner collaboration with peers and interaction with the course content, concurrently verifying learner identity and validating authorship of the academic artifacts. We present the preliminary results and discuss future directions.

Cite this work

No public copy is stored for this record, so only the metadata is cited.

Stored only when both papers are in the corpus — 19 citations exist upstream.

Papers that cite the same references — the relational fallback while embeddings are still backfilling.