Automated Essay Scoring With e-rater[R] V.2

Saved in:
Bibliographic Details
Title: Automated Essay Scoring With e-rater[R] V.2
Language: English
Authors: Attali, Yigal, Burstein, Jill
Source: Journal of Technology, Learning, and Assessment. Feb 2006 4(3).
Availability: Technology and Assessment Study Collaborative. 332 Campion Hall, Boston College, Chestnut Hill, MA 02467. Tel: 617-552-4521; Fax: 617-552-8419; e-mail: jtal_editor@bc.edu; Web site: http://escholarship.bc.edu/jtla
Peer Reviewed: Y
Physical Description: PDF
Page Count: 31
Publication Date: 2006
Document Type: Journal Articles
Reports - Descriptive
Education Level: Higher Education
Postsecondary Education
Descriptors: Educational Testing, Test Scoring Machines, Scoring, Writing Evaluation, Writing Tests, Essays, Automation, Essay Tests, Validity, Reliability, Student Evaluation, College Entrance Examinations, Computer Assisted Testing, Computer Software Evaluation, Educational Technology, Computer Software
ISSN: 1540-2525
Abstract: E-rater[R] has been used by the Educational Testing Service for automated essay scoring since 1999. This paper describes a new version of e-rater (V.2) that is different from other automated essay scoring systems in several important respects. The main innovations of e-rater V.2 are a small, intuitive, and meaningful set of features used for scoring; a single scoring model and standards can be used across all prompts of an assessment; modeling procedures that are transparent and flexible, and can be based entirely on expert judgment. The paper describes this new system and presents evidence on the validity and reliability of its scores. (Contains 2 endnotes, 9 tables, and 2 figures.)
Abstractor: As Provided
Number of References: 25
Entry Date: 2009
Accession Number: EJ843852
Database: ERIC
Description
Abstract:E-rater[R] has been used by the Educational Testing Service for automated essay scoring since 1999. This paper describes a new version of e-rater (V.2) that is different from other automated essay scoring systems in several important respects. The main innovations of e-rater V.2 are a small, intuitive, and meaningful set of features used for scoring; a single scoring model and standards can be used across all prompts of an assessment; modeling procedures that are transparent and flexible, and can be based entirely on expert judgment. The paper describes this new system and presents evidence on the validity and reliability of its scores. (Contains 2 endnotes, 9 tables, and 2 figures.)
ISSN:1540-2525