Publication type: Conference paper
Type of review: Peer review (abstract)
Title: EFL placement testing for engineering students with automated essay scoring : natural language processing in R
Authors: Gautschi, Curtis
et. al: No
Proceedings: Technische Bildung im Kontext von “Digitalisierung” / “Automatisierung” : Tendenzen, Möglichkeiten, Perspektiven : Wege zu technischer Bildung
Editors of the parent work: Petersen, Maren
Kammasch, Gudrun
Pages: 65
Pages to: 70
Conference details: 4. Ingenieurpädagogische Regionaltagung 2019, Universität Bremen, 23.-25. Mai 2019
Issue Date: 2020
Publisher / Ed. Institution: IPW
Publisher / Ed. Institution: Berlin
ISBN: 3-9818728-3-5
978-3-9818728-3-5
Language: English
Subjects: Automated essay scoring; Placement testing for writing; Computerized assessment; EFL writing assessment
Subject (DDC): 410.285: Computational linguistics
808: Rhetoric and writing
Abstract: This paper describes the design and first results of an Automated Essay Scoring tool and CEFR-level prediction algorithm created and experimentally implemented in an online English placement test in a higher-education setting. The algorithm was developed employing a prediction-accuracy pseudo-black box approach using a small training corpus of texts with known CEFR levels (N=48). Written and run entirely in R, the tool can be integrated with other advanced text analyses possible in R. Efficiently calculating the CEFR levels of large numbers of student essays, the tool is ideal for quick assessment of writing skills for placement purposes.
URI: https://digitalcollection.zhaw.ch/handle/11475/21340
Fulltext version: Published version
License (according to publishing contract): Licence according to publishing contract
Departement: Applied Linguistics
Organisational Unit: Institute of Language Competence (ILC)
Appears in collections:Publikationen Angewandte Linguistik

Files in This Item:
There are no files associated with this item.


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.