The use of rating and Likert scales in Natural Language Generation human evaluation tasks: A review and some recommendations
Open accessThe DOI matches its Crossref record; 7 of the 7 references it cites were found in a registry or an index.
Abstract
Rating and Likert scales are widely used in evaluation experiments to measure the quality of Natural Language Generation (NLG) systems.We review the use of rating and Likert scales for NLG evaluation tasks published in NLG specialized conferences over the last ten years (135 papers in total).Our analysis brings to light a number of deviations from good practice in their use.We conclude with some recommendations about the use of such scales.Our aim is to encourage the appropriate use of evaluation methodologies in the NLG community.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Likert scales, levels of measurement, and the “laws” of statistics
Norman, G. (2010) · Advances in Health Sciences Education · doi:10.1007/s10459-010-9222-y · Cited by 4,850 · cited 1×
“As proved by previous studies, see for example Norman (2010), the use of parametric statistics is quite robust with ordinal data.”
MethodLikert Scale: Explored and Explained
Joshi, A., Kale, S., Chandel, S., & Pal, D. (2015) · British Journal of Applied Science & Technology · doi:10.9734/bjast/2015/14975 · Cited by 3,870
Analyzing and Interpreting Data From Likert-Type Scales
Sullivan, G. M., & Artino, A. R. (2013) · Journal of Graduate Medical Education · doi:10.4300/jgme-5-4-18 · Cited by 3,044
Thanks coefficient alpha, we’ll take it from here.
McNeish, D. (2018) · Psychological Methods · doi:10.1037/met0000144 · Cited by 2,533
Analyzing ordinal data with metric models: What could possibly go wrong?
Liddell, T. M., & Kruschke, J. K. (2018) · Journal of Experimental Social Psychology · doi:10.1016/j.jesp.2018.08.009 · Cited by 805 · cited 1×
“Liddell and Kruschke (2018) present several problematic cases where parametric statistic were used for ordinal data.”
BackgroundOrdinal Regression Models in Psychology: A Tutorial
Bürkner, P.-C., & Vuorre, M. (2019) · Advances in Methods and Practices in Psychological Science · doi:10.1177/2515245918823199 · Cited by 689 · cited 1×
“…recent advances in statistics have introduced new options for ordinal data which are worth to be taken into account, for example ordinal regression models (B¨urkner and Vuorre, 2019) or generalized mixed effect models (Faraway, 2016) which are able to work with several different data distributions.”
BackgroundFive-Point Likert Items: t test versus Mann-Whitney-Wilcoxon (Addendum added October 2012)
de Winter, J. F. C., & Dodou, D. (2010) · University of Massachusetts Amherst · doi:10.7275/bj1p-ts64 · Cited by 231
Cited by
Best practices for the human evaluation of automatically generated text
van der Lee, C., Gatt, A., van Miltenburg, E., Wubben, S., & Krahmer, E. (2019) · Proceedings of the 12th International Conference on Natural Language Generation · doi:10.18653/v1/w19-8643 · Cited by 205
“Do note that Likert and rating scales are treated indistinctly here (for a distinction, see Amidei et al., 2019).”
BackgroundEvaluation of Text Generation: A Survey
Celikyilmaz, A., Clark, E., & Gao, J. (2020) · arXiv · doi:10.48550/arxiv.2006.14799 · Cited by 207
Repairing the Cracked Foundation: A Survey of Obstacles in Evaluation Practices for Generated Text
Gehrmann, S., Clark, E., & Sellam, T. (2023) · Journal of Artificial Intelligence Research · doi:10.1613/jair.1.13715 · Cited by 123
The Authenticity Gap in Human Evaluation
Ethayarajh, K., & Jurafsky, D. (2022) · Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing · doi:10.18653/v1/2022.emnlp-main.406 · Cited by 10
Metadata
- Authors
- Amidei, J., Piwek, P., & Willis, A.
- Venue
- Proceedings of the 12th International Conference on Natural Language Generation
- Published
- 2019
- Pages
- 397-402
- OpenAlex
- W2990527403
- Cited by
- 37
- References
- 7
- FWCI
- 1.10
- Type
- conference paper
- Language
- en
- Open access
- hybrid
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
How to cite
Cite CoChat for the checks on this page, and the paper for its own findings.
- This page
- CoChat. (2026). Citation check: The use of rating and Likert scales in Natural Language Generation human evaluation tasks: A review and some recommendations. https://app.cochat.ai/papers/10.18653/v1/w19-8648
- The paper
- Amidei, J., Piwek, P., & Willis, A. (2019). The use of rating and Likert scales in Natural Language Generation human evaluation tasks: A review and some recommendations. Proceedings of the 12th International Conference on Natural Language Generation. https://doi.org/10.18653/v1/w19-8648
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.