Publication Type : Conference Paper
Thematic Areas : Amrita e-Learning Research Lab
Publisher : 2017 International Conference on Advances in Computing, Communications and Informatics, ICACCI 2017
Source : 2017 International Conference on Advances in Computing, Communications and Informatics, ICACCI 2017, Institute of Electrical and Electronics Engineers Inc. (2017)
ISBN : 9781509063673
Keywords : calibration, Capture performance, Computer aided instruction, Distance education, E assessments, Evaluation methodologies, Feature extraction methods, Intelligent tutoring system, Learning systems, Performance metrics, Personalized learning, Question banks, Unsupervised learning
Campus : Amritapuri
School : School of Engineering
Center : E-Learning
Department : E-Learning, Electrical and Electronics
Year : 2017
Abstract : In traditional e-assessments as well as in personalized learning, question bank calibration plays an important role in ensuring high-quality assessment outcomes. We propose an unsupervised learning approach that uses performance metrics derived from test-taker responses for precise calibration of question banks. We show partitioning test-takers into three groups using their scores is an effective feature extraction method. This approach, enables us to accurately capture performance variations in test-taker sub-groups thereby effectively capturing inter-item correlations. Integration of such a Machine Learning (ML) approach into the Question Bank module of a cloudbased e-assessment system enables seamless automatic question calibration. We validate the effectiveness of our approach, using a large dataset, collected from a two thousand student universitylevel proctored assessment.
Cite this Research Publication : S. Narayanan, Kommuri, V. S., Subramanian, S. N., and Kamal Bijlani, “Question Bank Calibration using Unsupervised Learning of Assessment Performance Metrics”, in 2017 International Conference on Advances in Computing, Communications and Informatics, ICACCI 2017, 2017.