Year : 2019, Volume : 9, Issue : 1
First page : ( 1) Last page : ( 10)
Print ISSN : 2249-3212. Online ISSN : 2249-3220.
Article DOI : 10.5958/2249-3220.2019.00001.6

Apriori Extractor and Binomial Heap Extractor — A Comparison

Paul Dimple V.^1,*

¹Assistant Professor, Department of Computer Science, Dnyanprassarak Mandal's College and Research Centre, Assagao, Bardez, Mapusa-403507, Goa, India

*Email id: dimplevp@rediffmail.com

Received:  05  December,  2018; Accepted:  19  February,  2019.

Abstract

We present an information extraction technique for automatically extracting keywords from textual documents. Automatic Extraction of Keywords using Frequent Item sets (AEKFI) is a novel technique for keyword extraction which integrates adjacency of location of words within the document to automatically select the most discriminative words without using a corpus. It consist of three major phases, namely text pre-processing phase for performing tokenisation; stemming and stop word removal, frequent item-set extraction phase for applying the designed apriori and binomial heap-based approaches ingenerating the set of keywords and visualisation phase for carrying out presentation of the set of keywords. AEKFI gives flexibility to select either the set of keywords from a given document or user-specified number of keywords. There is no restriction to the length of keywords being extracted. Demonstrations of keyword extraction using apriori approach and binomial minimum heap approach have been made to compare their performances. Experimental results prove the advantage of binomial minimum heap-based AEKFI over other keyword extraction tools.

Top

Keywords

Text pre-processing, Association rule, Frequent itemsets, Apriori algorithm, Binomial heap, Dense words.

Top