An Enhanced Arabic Information Retrieval Using Genetic Algorithms: An Experimental Study and Results

EasyChair Preprint 4468

Abstract

Many key challenges influence on the use of Arabic information retrieval systems, one of these is the performance of the Arabic information retrieval systems in terms of precision and recall. In this paper, we present the Genetic Algorithms to improve performance of Arabic information retrieval system based on vector space model. The main idea in this paper is the usage of an adaptive matching function, which obtained from a weighted combination of four similarity measures (Dot, Cosine, Jaccard, and Dice). The Genetic Algorithms used to optimize these matching functions, through obtaining the best achievable combination of these weights. The proposed genetic process is tested on Arabic documents collection and then results has shown a considerable improvement on the precision as performance measure

Keyphrases: ArabicInformation Retrieval, Genetic Algorithm, Vector Space Model, recision

@booklet{EasyChair:4468,
  author    = {Bassam Al-Shargabi and Omar Sabri and Shadi Aljawarneh},
  title     = {An Enhanced Arabic Information Retrieval Using Genetic Algorithms: An Experimental Study and Results},
  howpublished = {EasyChair Preprint 4468},
  year      = {EasyChair, 2020}}