Challenges to the Use of Artificial Neural Networks for Diagnostic Classifications with Student Test Data

Autor/inn/en	Briggs, Derek C.; Circi, Ruhan
Titel	Challenges to the Use of Artificial Neural Networks for Diagnostic Classifications with Student Test Data
Quelle	In: International Journal of Testing, 17 (2017) 4, S.302-321 (20 Seiten)Infoseite zur Zeitschrift PDF als Volltext Verfügbarkeit
Zusatzinformation	ORCID (Briggs, Derek C.)
Sprache	englisch
Dokumenttyp	gedruckt; online; Zeitschriftenaufsatz
ISSN	1530-5058
DOI	10.1080/15305058.2017.1297816
Schlagwörter	Artificial Intelligence; Classification; Student Evaluation; Tests; Evaluation Methods; Multiple Choice Tests; Science Tests; Scientific Concepts; Physics; Responses; Prediction; Probability; High School Students; Iowa + Suchen Sie Ihr Suchwort? Künstliche Intelligenz; Classification system; Klassifikation; Klassifikationssystem; Schulnote; Studentische Bewertung; Examination; Prüfung; Examen; Multiple choice examinations; Multiple-choice tests, Multiple-choice examinations; Multiple-Choice-Verfahren; Physik; Vorhersage; Wahrscheinlichkeitsrechnung; Wahrscheinlichkeitstheorie; High school; High schools; Student; Students; Oberschule; Schüler; Schülerin; Studentin
Abstract	Artificial Neural Networks (ANNs) have been proposed as a promising approach for the classification of students into different levels of a psychological attribute hierarchy. Unfortunately, because such classifications typically rely upon internally produced item response patterns that have not been externally validated, the instability of ANN estimates of attribute probabilities may not be widely appreciated. The present study illustrates the problem with both empirical and simulated data. In particular, it is shown that when an ANN is "trained" multiple times using the same data, attribute probability estimates can vary, sometimes dramatically. Researchers hoping to apply ANNs in the context of diagnostic classification models with student test data need to be very deliberate in checking the sensitivity of their findings. (As Provided).
Anmerkungen	Routledge. Available from: Taylor & Francis, Ltd. 530 Walnut Street Suite 850, Philadelphia, PA 19106. Tel: 800-354-1420; Tel: 215-625-8900; Fax: 215-207-0050; Web site: http://www.tandf.co.uk/journals
Erfasst von	ERIC (Education Resources Information Center), Washington, DC
Update	2020/1/01