-
-
Autor*innen: Zehner, Fabian; Sälzer, Christine; Goldhammer, Frank
Titel: Automatic coding of short text responses via clustering in educational assessment
In: Educational and Psychological Measurement, 76 (2016) 2, S. 280-303
DOI: 10.1177/0013164415590022
URN: urn:nbn:de:0111-pedocs-149795
URL: https://nbn-resolving.org/urn:nbn:de:0111-pedocs-149795
Dokumenttyp: 3a. Beiträge in begutachteten Zeitschriften; Aufsatz (keine besondere Kategorie)
Sprache: Englisch
Schlagwörter: Antwort; Automatisierung; Codierung; Computerlinguistik; Leistungstest; Methode; PISA <Programme for International Student Assessment>; Software; Technologiebasiertes Testen; Testkonstruktion
Abstract: Automatic coding of short text responses opens new doors in assessment. We implemented and integrated baseline methods of natural language processing and statistical modelling by means of software components that are available under open licenses. The accuracy of automatic text coding is demonstrated by using data collected in the Programme for International Student Assessment (PISA) 2012 in Germany. Free text responses of 10 items with Formula responses in total were analyzed. We further examined the effect of different methods, parameter values, and sample sizes on performance of the implemented system. The system reached fair to good up to excellent agreement with human codings Formula Especially items that are solved by naming specific semantic concepts appeared properly coded. The system performed equally well with Formula and somewhat poorer but still acceptable down to Formula Based on our findings, we discuss potential innovations for assessment that are enabled by automatic coding of short text responses. (DIPF/Orig.)
DIPF-Abteilung: Bildungsqualität und Evaluation