View in EDS

Automated Essay Scoring with e-rater® v.2.0. Research Report. ETS RR-04-45

Saved in:
Bibliographic Details
Title: Automated Essay Scoring with e-rater® v.2.0. Research Report. ETS RR-04-45
Language: English
Authors: Attali, Yigal, Burstein, Jill
Source: ETS Research Report Series. Nov 2005 (v).
Availability: Educational Testing Service. Rosedale Road, MS19-R Princeton, NJ 08541. Tel: 609-921-9000; Fax: 609-734-5410; e-mail: RDweb@ets.org; Web site: https://www.ets.org/research/policy_research_reports/ets
Peer Reviewed: Y
Page Count: 25
Publication Date: 2005
Document Type: Journal Articles
Reports - Research
Education Level: Higher Education
Postsecondary Education
Grade 6
Intermediate Grades
Middle Schools
Elementary Education
Grade 7
Junior High Schools
Secondary Education
Grade 8
Grade 9
High Schools
Grade 10
Grade 11
Grade 12
Descriptors: Essay Tests, Automation, Scoring, Comparative Analysis, Validity, Reliability, Business Administration Education, Business Schools, College Entrance Examinations, Graduate Study, Language Tests, English (Second Language), Second Language Learning, Writing Tests, Grade 6, Grade 7, Grade 8, Grade 9, Grade 10, Grade 11, Grade 12
Assessment and Survey Identifiers: Graduate Management Admission Test, Test of English as a Foreign Language
ISSN: 2330-8516
Abstract: The e-rater® system has been used by ETS for automated essay scoring since 1999. This paper describes a new version of e-rater (v.2.0) that differs from the previous one (v.1.3) with regard to the feature set and model building approach. The paper describes the new version, compares the new and previous versions in terms of performance, and presents evidence on the validity and reliability of scores produced by the new version.
Abstractor: As Provided
Number of References: 7
Entry Date: 2016
Accession Number: EJ1110978
Database: ERIC
Description
Abstract:The e-rater® system has been used by ETS for automated essay scoring since 1999. This paper describes a new version of e-rater (v.2.0) that differs from the previous one (v.1.3) with regard to the feature set and model building approach. The paper describes the new version, compares the new and previous versions in terms of performance, and presents evidence on the validity and reliability of scores produced by the new version.
ISSN:2330-8516