Intuitionistic Group Decision Making to Identify the Status of Student's Knowledge Acquisition in E-Learning Systems

Intuitionistic Group Decision Making to Identify the Status of Student's Knowledge Acquisition in E-Learning Systems

Mukta Goyal (Department of Computer Science, Jaypee Institute of Information Technology, Noida, India), Alka Tripathi (Department of Mathematics, Jaypee Institute of Information Technology, Noida, India) and Divakar Yadav (Department of Computer Science, Jaypee Institute of Information Technology, Noida, India)
Copyright: © 2016 |Pages: 16
DOI: 10.4018/IJFSA.2016070102
OnDemand PDF Download:
$30.00
List Price: $37.50

Abstract

Learner's performance evaluation in an E-learning environment is a multi-criteria decision problem and important to personalize the sequence of learning concepts according to their knowledge level. Crisp responses, leads uncertainty in the evaluation process due to successful guesses or choosing a more probable answer. Analysis of learner's response to a complex/subjective questions needs more effort. Moreover, due to uncertainty and imprecise nature of learner, traditional methods are inadequate to assess, how much time he has spent on studying the learning contents and also the number of backtracking he followed. This paper proposes an intuitionistic fuzzy multicriteria decision making that investigates the use of an intuitionistic fuzzy technique for order preference by similarity to ideal solution (TOPSIS method) for the evaluation of student in an E-learning environment. Synthetic data are created for the criteria's that affect the student evaluation in E-learning domain and thereafter results are evaluated.
Article Preview

Introduction

The term E- learning used for education through electronic means uses telecommunication technology to deliver information. For consistent delivery of learning content on demand, E-learning systems require to feature learner’s preferences, interests and browsing behaviors to offer personalized services. This need brings out the concept of adaptive E-learning systems (Brusilovsky, 1998). Adaptive E-learning is an educational method which uses computers as interactive teaching devices. Computers adapt the presentation of educational materials according to student’s weaknesses, as indicated by their responses to questions (Brusilovsky & Peylo, 2003). Adaptive E-learning systems collect data for the user model from various sources such as implicitly observing user’s interaction with the system through eye tracking or calculating time, how much time she spent on reading a content etc. or explicitly requesting direct input from the users. This data is processed and updated which is known as user modeling (Brusilovsky, 1998). The system has to deliver with the adaptation effect that depend on the information, represented in the user model. Due to imprecise nature of human being, user modeling faces the challenges to capture the user features (Frías-Martínez et al., 2004). Zadeh (1965) proposed a fuzzy set theory which is very effective for such cases to handle the vagueness and uncertainty in the knowledge possessed by people. In fuzzy set theory, the membership of an element to a fuzzy set is a single value between zero and one. However, in reality it is not always true that the degree of non-membership of an element in a fuzzy set is equal to 1 minus the membership degree because there may be some hesitation degree also. Therefore, a generalization of fuzzy sets was proposed by Atanassov (1986, 1999) intuitionistic fuzzy sets (IFS) which incorporates the degree of hesitation called hesitation margin. Hesitation margin is defined as 1 minus the sum of membership and non-membership degree respectively. The applications of intuitionistic fuzzy sets are decision making, medical diagnosis, pattern recognition, market prediction, facility location selection etc. Various decision making and selection problem can be solved through multiple attribute decision making (MADM) (Rouyendegh, 2012).

Due to the flexibility of IFS in handling uncertainty, it provides more human consistent reasoning under imperfectly defined facts and imprecise knowledge. Knowledge is structured information and knowledge acquisition is done through learning and experience. Knowledge representation and processing are the keys to any intelligent system. In E-learning these intelligent systems uses the automated comprehension -type exams such as true/ false, multiple choice questions, matching ordering, sorting, text analysis of short- answers, essays, message boards and discussion boards to acquire the learner's knowledge. Knowledge acquisition also includes tracking of learner's participation and time to learn any learning material. However, most of these learning systems determine the learner's knowledge through crisp responses. Few researchers (Hosseini and Kardan, 2011) have used intuitionistic fuzzy approach to assess the learner's response to incorporate the uncertainty about the evaluation process such as successful guesses or choosing a more probable answer. Analysis of learner’s response to a complex/subjective question needs more efforts. Learner's participation, while studying the learning content requires careful assessment. During learning the study material, it is possible that learner might not be attentive, so it is required to assess the learner's knowledge carefully in E-learning system.

Hence this paper proposes an intuitionistic fuzzy multi-criteria group decision making with TOPSIS method to identify the status of knowledge acquisition of student in E-learning system. The importance of the attributes and the impact of these attributes to the uncertainty in the knowledge acquisition of the student play a major role. In an evaluation process of student, aggregation of the expert’s opinion is also very important. Therefore, all individual expert’s opinion for rating the criteria and alternatives which represent students are aggregated by IFWA (intuitionistic fuzzy weighted averaging) operator (Xu, 2007). In multi-criteria decision making, the TOPSIS method considers both positive ideal and negative ideal solution and gives systematic and consistent ranking.

Complete Article List

Search this Journal:
Reset
Open Access Articles: Forthcoming
Volume 6: 4 Issues (2017)
Volume 5: 4 Issues (2016)
Volume 4: 4 Issues (2015)
Volume 3: 4 Issues (2013)
Volume 2: 4 Issues (2012)
Volume 1: 4 Issues (2011)
View Complete Journal Contents Listing