ACQUA: Automated Community-based Question Answering through the Discretisation of Shallow Linguistic Features
- Submitting institution
-
The Open University
- Unit of assessment
- 11 - Computer Science and Informatics
- Output identifier
- 1453481
- Type
- D - Journal article
- DOI
-
10.1561/106.00000001
- Title of journal
- Journal of Web Science
- Article number
- -
- First page
- 1
- Volume
- 1
- Issue
- 1
- ISSN
- 2332-4031
- Open access status
- Out of scope for open access requirements
- Month of publication
- June
- Year of publication
- 2015
- URL
-
http://www.webscience-journal.net/webscience/article/view/13
- 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)
-
-
- Citation count
- -
- Proposed double-weighted
- No
- Reserve for an output with double weighting
- No
- Additional information
- This paper, published in the Journal of Web Science, finds the best answer to web community questions with particularly lightweight requirements in terms of input. This is significant due to the sheer size of such sites (StackOverflow, one of the websites we analysed serves 100M users a month). It still outperforms most of the competition as also found by an external study (Calefato et al., 2016). Our ‘discretization of features’ technique was found (Calefato et al., 2019) to enhance the robustness best-answer prediction classifiers across heterogenous Q&A sites extending the application range for these types of support systems.
- Author contribution statement
- -
- Non-English
- No
- English abstract
- -