Near Real-Time Comprehension Classification with Artificial Neural Networks: Decoding e-Learner Non-Verbal Behavior
- Submitting institution
-
Manchester Metropolitan University
- Unit of assessment
- 11 - Computer Science and Informatics
- Output identifier
- 2340
- Type
- D - Journal article
- DOI
-
10.1109/TLT.2017.2754497
- Title of journal
- IEEE Transactions on Learning Technologies
- Article number
- -
- First page
- 5
- Volume
- 11
- Issue
- 1
- ISSN
- 1939-1382
- Open access status
- Compliant
- Month of publication
- September
- Year of publication
- 2017
- URL
-
https://e-space.mmu.ac.uk/619143/
- Supplementary information
-
-
- Request cross-referral to
- -
- Output has been delayed by COVID-19
- No
- COVID-19 affected output statement
- -
- Forensic science
- No
- Criminology
- No
- Interdisciplinary
- No
- Number of additional authors
-
3
- Research group(s)
-
C - Machine Intelligence
- Citation count
- 12
- Proposed double-weighted
- No
- Reserve for an output with double weighting
- No
- Additional information
- This paper proposes COMPASS, a novel image-processing algorithm and classifier for scoring e-learner comprehension of on-screen information using webcam images. Its key contribution is to overcome previous limitations (fixed lighting, distance and subject positioning) to deliver a practical, low-cost, non-intrusive way of classifying comprehension in near-real time during human-computer interactions. Its model of learner non-verbal behaviour has applications in e-learning and domains where detection of user comprehension is critical (e.g. informed consent). Built on Silent Talker (Rothwell et.al, 2006), this work provided evidence to support automated adaptive psychological profiling from non-verbal behaviour which led to H2020 funding for iBorderCtl (700626).
- Author contribution statement
- -
- Non-English
- No
- English abstract
- -