earticle

논문검색

A Self Intelligent Learner Identification to Increase Self-Efficacy for Enhanced Learning Performance

초록

영어

Students’ performance on learning is based on the Self-Efficacy and mental efforts. Learning style of a person will be changing based on the environment. Our objective is to improve the self-efficacy and provide the learning content based on the learning style adopted by the learner. This study attempt has been made to classify the e-learning user based on their opinion on a set of parameters. e-learners before commencing their learning process are asked to record their opinion on 16 parameters of a five point scale. 367 e-learners were provided the responses. Based on the responses, the users were categorized to different categories on a statically using factor analysis. The factor analysis provides five components. The components were named based on variables. Thus users were grouped as Multimedia, Modality,Contiguity, Redundancy and personalization learners. A real time agent has also been developed to categorize e-learners based on the 16 parameters thus used in statistical method has also been used. This agent will provide the suitable e-learning content based on the current learning style of the users. This helps in better understanding of the concept. The real time agent categorized the user and the results were compared with statistical method. Moreover, the proposed system analyses the error rate on learning style identified by the system and the one who posses naturally. Out of the 367 users, the real time system identified 357 learners same as in the statistical method with the error rate of 0.046296. Since the error rate was minimal the system thus developed was reliable. Further erroneously categorized by the real time systems were identified and compared with the statistical method. The content of e-learning was delivered to the user by the server according to the type of users based on statistical method. For the remaining 10 users the content were reorganized and delivered to the learner statistically categorized and as well as the real time system category.

목차

Abstract
 1. Introduction
 2. E-Learning
  2.1. Learning Styles
 3. Reliability Test (Cronbach’s Alpha)
 4. Factor Analysis
 5. Proposed Architecture
 6. Statistical Test for Learner Classification and Content Development
  6.1. Learner Classification and Content Development
  6.2. Decision Box as Content Classifier
 7. Conclusions
 References

저자정보

  • M. Mohammed Thaha Research Scholar, Department of Computer Science and Engineering Sri Venkateswara College of Engineering, Pennalur, Chennai, India
  • C. Jayakumar Professor & Head of the Department, Department of Computer science and Engineering, Department of Computer Science and Engineering Sri Venkateswara College of Engineering, Pennalur, Chennai, India

참고문헌

자료제공 : 네이버학술정보

    함께 이용한 논문

      ※ 원문제공기관과의 협약기간이 종료되어 열람이 제한될 수 있습니다.

      0개의 논문이 장바구니에 담겼습니다.