Bayesian Performance Comparison of Text Classifiers
- Submitting institution
-
Birkbeck College
- Unit of assessment
- 11 - Computer Science and Informatics
- Output identifier
- 13
- Type
- E - Conference contribution
- DOI
-
10.1145/2911451.2911547
- Title of conference / published proceedings
- Proceedings of the 39th International ACM SIGIR conference on Research and Development in Information Retrieval - SIGIR '16
- First page
- 15
- Volume
- -
- Issue
- -
- ISSN
- -
- Open access status
- -
- Month of publication
- July
- Year of publication
- 2016
- URL
-
https://dl.acm.org/doi/10.1145/2911451.2911547
- 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)
-
2 - Experimental Data Science
- Citation count
- 10
- Proposed double-weighted
- No
- Reserve for an output with double weighting
- No
- Additional information
- This is one of the earliest papers to introduce Bayesian hypothesis testing to the field of information retrieval. The paper is of importance to information retrieval researchers because it provides a method to estimate the uncertainty of the very widely used F-measures, for example informing work by Tetsuya Sakai on developing a complete statistical framework for information retrieval evaluation. The source code and experimental datasets have been released (https://github.com/dell-zhang/bperf).
- Author contribution statement
- -
- Non-English
- No
- English abstract
- -