Publication Type : Conference Paper
Thematic Areas : Amrita e-Learning Research Lab
Publisher : 2018 International Conference on Data Science and Engineering, ICDSE 2018, Institute of Electrical and Electronics Engineers Inc.
Source : 2018 International Conference on Data Science and Engineering, ICDSE 2018, Institute of Electrical and Electronics Engineers Inc. (2018)
Url : https://www2.scopus.com/inward/record.uri?eid=2-s2.0-85058271251&doi=10.1109%2fICDSE.2018.8527800&partnerID=40&md5=78dbaa5affa7daea585e98d351361cf1
ISBN : 9781538648551
Keywords : Adaptive learning systems, Automatic calibration, Communication channels (information theory), Computer aided instruction, Data set, Evaluation methodologies, Gaussian distribution, Gaussian Mixture Model, Intelligent tutoring system, Item difficulties, Object recognition, Personalized learning, Petroleum reservoir evaluation.
Campus : Amritapuri
School : Department of Learning
Center : E-Learning
Department : E-Learning
Year : 2018
Abstract : The difficulty level of an assessment item plays an important role in ensuring well qualified evaluation process as well as helping in the generation of appropriate assessments for personalized learning. AMrita Personalized Learning and Evaluation (AMPLE) platform adopts an automatic calibration methodology using Gaussian Mixture Models for difficulty level assignment. This methodology uses performance features derived from the test-takers responses recorded in the assessment engine. Verification of this model, carried out on a diverse data set of assessment items spread over six subjects and 6000 students achieved about 91% accuracy by comparing the model-generated output with teacher-supplied difficulty levels.
Cite this Research Publication : S. Narayanan, Saj, F. M., Soumya, M. D., and Kamal Bijlani, “Predicting Assessment Item Difficulty Levels Using a Gaussian Mixture Model”, in 2018 International Conference on Data Science and Engineering, ICDSE 2018, 2018.