The E-rater® Automated Essay Scoring System
Abstract
In this chapter, we provide an overview of different methods used in scaling and norming essay scores starting with a general comparison of holistic and analytic rubrics. Next, scales applied for rating the quality of writing samples are reviewed with a focus on standardized writing development scales established for application in automated essay evaluation (AEE) providing for an examinee’s writing ability to be meaningfully tracked over time and across essay prompts. Methods for formation of scores in AEE are then overviewed. Common standard-setting methods are summarized and, finally, differential item functioning methods are discussed. Throughout the chapter, we raise validity issues that continue to exist today, and make recommendations for future work in the effort of producing meaningful scores in the process of scaling and norming essay scores in general and in AES.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
The e-rater scoring engine of the Educational Testing Service provides writing quality measures.
“writing quality measures by the e-rater scoring engine of the Educational Testing Service (ETS)23”
From Stress and productivity patterns of interrupted, synergistic, and antagonistic office activities (2019) · cites this paper as [23]
Cited by
Sorted by citations
Stress and productivity patterns of interrupted, synergistic, and antagonistic office activities
Zaman, S., Wesley, A., Silva, D. R. D. C., Buddharaju, P., Akbar, F., Gao, G., Mark, G., Gutierrez-Osuna, R., & Pavlidis, I. (2019) · Scientific Data · doi:10.1038/s41597-019-0249-5 · Cited by 17 · see citing works
- Venue
- Handbook of Automated Essay Evaluation
- Publisher
- Routledge
- Published
- 2013-07-18
- Pages
- 77-89
- Cited by
- 8
- References
- 0
- Language
- en
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
