Advertisement

A Semantic Approach of Building Dynamic Learner Profile Model Using WordNet

  • T. SheebaEmail author
  • Reshmy Krishnan
Conference paper
  • 39 Downloads
Part of the Advances in Intelligent Systems and Computing book series (AISC, volume 1082)

Abstract

The learners’ interest forms the essential characteristics of the learner profile in various applications, such as information retrieval, classification, and recommender systems. This paper proposes a method to improve learner interest extraction from the frequently used documents of the learner by exploring the concept of WordNet. Initially, the web log files of each learner are obtained from the learning management system, and then the frequently visited documents of each learner are downloaded and processed to identify domain-related words. The learner’s interest is then extracted initially using the standard vector space model and then improved using the semantic-based representation of WordNet. The WordNet identifies a set of semantic concepts related to the document words. To select the appropriate meaning of a word from a set of concepts, “Word Sense Disambiguation (WSD)” semantic similarity algorithm is used. The experiments were performed in NetBeans IDE using Java language and WordNet 2.1. The effect of the proposed method is examined with classification experiments, and the result proved that the use of WordNet concepts in learner interest retrieval shows better classification performance than compared to the existing method of term representation, thereby obtaining a classification accuracy of 89%.

Keywords

Dynamic learner profile WordNet Learner interest Semantic representation Word sense disambiguation 

References

  1. 1.
    Ahmad, A., Kardan., Farahmandnia, F., Omidvar, A.: A novel approach for keyword extraction in learning objects using text mining and WordNet. Glob. J. Inf. Technol. 3(1), 1–6 (2013)Google Scholar
  2. 2.
    Thakyhkar, A., Chauhan, S.: A novel approach for keyword extraction in learning objects using text mining. IJARIIE. 2(3), 2395–4396 (2016)Google Scholar
  3. 3.
    Menaka, S., Radha, N.: Text classification using keyword extraction technique. Int. J. Adv. Res. Comput. Sci. Softw. Eng. 3(12), 734–740 (2013)Google Scholar
  4. 4.
    Fouad, K.M.: Adaptive E-learning system based on semantic web and fuzzy clustering. Int. J. Comput. Sci. Inf. Secur. 8(9), 308–315 (2010)Google Scholar
  5. 5.
    Porter, M.: An algorithm for suffix stripping. Program Electron. Libr. Inf. Syst. 14 (3), pp. 130–137 (1980)Google Scholar
  6. 6.
    Biasiotti, M., Francesconi, E., Palmirani, M., Sartor, G., Vitali, F.: Legal informatics and management of legislative documents. Global Centre for ICT in Parliament, Working Paper, vol. 2, pp. 62–76 (2008)Google Scholar

Copyright information

© Springer Nature Singapore Pte Ltd. 2020

Authors and Affiliations

  1. 1.Department of Computer Science & EngineeringKarpagam UniversityCoimbatoreIndia
  2. 2.Department of ComputingMuscat CollegeRuwiOman

Personalised recommendations