Implementation of an efficient Fuzzy Logic based Information Retrieval System

Authors

  • Prabhjot Singh Bharati Vidyapeeth's College of Engineering
  • Sumit Dhawan Bharati Vidyapeeth's College of Engineering
  • Shubham Agarwal Bharati Vidyapeeth's College of Engineering
  • Narina Thakur Bharati Vidyapeeth's College of Engineering

DOI:

https://doi.org/10.4108/sis.2.5.e5

Keywords:

Fuzzy Logic, Information Retrieval, Similarity, Precision, Recall, Lucene

Abstract

This paper exemplifies the implementation of an efficient Information Retrieval (IR) System to compute the similarity between a dataset and a query using Fuzzy Logic. TREC (Text Retrieval Conference) dataset has been used for the implementation purpose. The dataset is parsed to generate keywords index which is used for the similarity comparison with the user query. Each query is assigned a score value based on its fuzzy similarity with the index keywords. The relevant documents are retrieved based on the score value. The performance and accuracy of the proposed fuzzy similarity model is compared with Cosine similarity model using Precision-Recall curves. The results prove the dominance of Fuzzy Similarity based IR system.

Downloads

Published

02-07-2015

How to Cite

1.
Singh P, Dhawan S, Agarwal S, Thakur N. Implementation of an efficient Fuzzy Logic based Information Retrieval System. EAI Endorsed Scal Inf Syst [Internet]. 2015 Jul. 2 [cited 2024 Nov. 13];2(5):e5. Available from: https://publications.eai.eu/index.php/sis/article/view/2304