Automatically Learning Topics and Difficulty Levels of Problems in Online Judge Systems
- Submitting institution
-
Aston University
- Unit of assessment
- 11 - Computer Science and Informatics
- Output identifier
- 24402350
- Type
- D - Journal article
- DOI
-
10.1145/3158670
- Title of journal
- ACM Transactions on Information Systems
- Article number
- 27
- First page
- -
- Volume
- 36
- Issue
- 3
- ISSN
- 1046-8188
- Open access status
- Compliant
- Month of publication
- March
- Year of publication
- 2018
- URL
-
-
- 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
-
4
- Research group(s)
-
A - Aston Institute of Urban Technology and the Environment (ASTUTE)
- Citation count
- 9
- Proposed double-weighted
- No
- Reserve for an output with double weighting
- No
- Additional information
- The paper presents the first attempt of extracting topics and predicting difficulty levels of problems in online judge systems. The proposed two-mode Hidden Markov Topic Model was built on rigorous investigation of large-scale user behaviour in attempting problems in online judge systems. The great potential of the work for revolutionising research in learning analytics is evidenced by the fact it has impacted work on student performance prediction (Xiong, Rutgers), recommender in online education systems (Zhai, UIUC), and tracking the knowledge proficiency of students (Xiao, Stony Brook).
- Author contribution statement
- -
- Non-English
- No
- English abstract
- -
