Article Preview
Top1. Introduction
Outcome based education (OBE) (Spady & Marshall, 1991; Spady, 1994) has become a need of the hour and it has two components towards its achievements. One is increasing the students’ attainment level and other one is to fill the gap in acquired knowledge which can enhance the students attainments if it is identified and bridged properly. Human tutors traditionally perform these tasks of identification and bridging the knowledge gap (Das et al., 2017; Rolandsson et al., 2017). With the increase of number of students in the process, human tutors face many problems towards the above identification and knowledge filling. These also advocates some paradigm shift in the educational activities where learners themselves take very important roles and teachers acts as facilitators. Knowledge gap residing in any student should properly be identified and remedial measures regarding this have to be taken. Finding the knowledge gap requires finding the gap of knowledge delivered to the students through different tutorials on each subtopic of a course.
Thus, learner centric education is a regulatory requirement now a day's all over the world. The paradigm shift of the educational distribution also observed a change through implementation of blended form of education where learners themselves are in the process of identifying their own knowledge gaps. Normally, human tutors take the role of identifying student’s educational shortcomings through different tests and interactions. Many of the learners’ educational deficiencies are taken care through tutorial classes may be with focused group or clusters of students. But identification of requirements of such tutorials are analyzed by human tutors in face-to-face mode. But such student modeling becomes more complicated and problematic with the number of students and hence educators offer some ICT tools (Zealand,2003) for the purpose along with the facilities for blended form of education. Intelligent Tutoring System (ITS) (Bag & Das, 2010) are one of those ICT tools which take care the role of students modeling with the use of different intelligent computational processes.
Student modeling in e-learning is a serious matter of concern which is generally formulated with the interactions of learners with the automatic learning systems. Students are given MCQ test sets to solve after going through a piece of content based on some topic or subtopics (Gokmen et al., 2010; Barlybayev et al. 2016). Those test responses are analyzed through some computational methods and learners’ tutorial need may be identified which is done be experienced human tutors very accurately with their enhanced experiences of students dealings. As the human tutors are experiencing teaching, he is more accurately identifying the student’s tutorial needs as he comes to decision regarding tutorial needs from fuzzy to crisp articulation capabilities running in his back of mind. Likewise, ITS should incorporate some fuzzy logic to identify learner’s tutorial needs through analysis of learner’s responses to MCQ tests may be.
Tutorial gap (Das et al., 2017) measurement is done by using traditional way of numeric calculations. In this traditional method, tutorial gap is calculated, from the score obtained by a student in the evaluation process, by using some mathematical formula. This traditional way of finding tutorial gap produces rigid numeric values, which often may be unrealistic. This is because only numerically calculated values do not reflect the actual scenario correctly always. This inappropriate measurement can be rectified and blended with the realistic and flexible approach provided by fuzzy logic (Zadeh, 1965; Bose & Das, 2015; Mitra & Das, 2015). This paper focuses on the application of fuzzy logic to find the tutorial gap by taking the advantages of fuzzy logic over conventional method.