Amortised Design Optimization for Item Response Theory

Antti Keurulainen*, Isak Westerlund, Oskar Keurulainen, Andrew Howes

*Tämän työn vastaava kirjoittaja

Tutkimustuotos: Artikkeli kirjassa/konferenssijulkaisussaConference article in proceedingsScientificvertaisarvioitu

1 Sitaatiot (Scopus)

Abstrakti

Item Response Theory (IRT) is a well known method for assessing responses from humans in education and psychology. In education, IRT is used to infer student abilities and characteristics of test items from student responses. Interactions with students are expensive, calling for methods that efficiently gather information for inferring student abilities. Methods based on Optimal Experimental Design (OED) are computationally costly, making them inapplicable for interactive applications. In response, we propose incorporating amortised experimental design into IRT. Here, the computational cost is shifted to a precomputing phase by training a Deep Reinforcement Learning (DRL) agent with synthetic data. The agent is trained to select optimally informative test items for the distribution of students, and to conduct amortised inference conditioned on the experiment outcomes. During deployment the agent estimates parameters from data, and suggests the next test item for the student, in close to real-time, by taking into account the history of experiments and outcomes.

AlkuperäiskieliEnglanti
OtsikkoArtificial Intelligence in Education. Posters and Late Breaking Results, Workshops and Tutorials, Industry and Innovation Tracks, Practitioners, Doctoral Consortium and Blue Sky - 24th International Conference, AIED 2023, Proceedings
ToimittajatNing Wang, Genaro Rebolledo-Mendez, Vania Dimitrova, Noboru Matsuda, Olga C. Santos
KustantajaSpringer
Sivut359-364
Sivumäärä6
ISBN (painettu)978-3-031-36335-1
DOI - pysyväislinkit
TilaJulkaistu - 2023
OKM-julkaisutyyppiA4 Artikkeli konferenssijulkaisussa
TapahtumaInternational Conference on Artificial Intelligence in Education - Tokyo, Japani
Kesto: 3 heinäk. 20237 heinäk. 2023
Konferenssinumero: 24

Julkaisusarja

NimiCommunications in Computer and Information Science
Vuosikerta1831 CCIS
ISSN (painettu)1865-0929
ISSN (elektroninen)1865-0937

Conference

ConferenceInternational Conference on Artificial Intelligence in Education
LyhennettäAIED
Maa/AlueJapani
KaupunkiTokyo
Ajanjakso03/07/202307/07/2023

Sormenjälki

Sukella tutkimusaiheisiin 'Amortised Design Optimization for Item Response Theory'. Ne muodostavat yhdessä ainutlaatuisen sormenjäljen.

Siteeraa tätä