Dechawut WanichsanPatcharin PanjabureeParames LaosinchaiWannapong TriampoSasithorn ChookaewMahidol University2018-06-112018-06-112012-07-01Expert Systems with Applications. Vol.39, No.9 (2012), 8380-8388095741742-s2.0-84858339083https://repository.li.mahidol.ac.th/handle/20.500.14594/14046In the recent years, diagnosing students' learning problems after testing and providing learning suggestions for them are an important research issue. Many studies have been conducted to develop a method for analyzing learning barriers of students such that helpful learning suggestions or guidance can be provided based on the analysis results. In this paper, we present a new procedure for integrating test item-concept relationship opinions based on majority density of multiple experts in order to enhance a concept-effect relationship model used for generating personalized feedback. It provides a useful and practical way to decrease inconsistencies in the weighting criteria of multiple experts and to enhance the entire learning-diagnosis procedure for developing testing and diagnostic systems. © 2012 Elsevier Ltd. All rights reserved.Mahidol UniversityComputer ScienceEngineeringArticleSCOPUS10.1016/j.eswa.2012.01.182