Open AccessDOMAIN SPECIFIC KEY FEATURE EXTRACTION USING KNOWLEDGE GRAPH MINING
Author(s) -
Mohit Kumar Barai,
AUTHOR_ID,
Subhasis Sanyal,
AUTHOR_ID
Publication year - 2020
Publication title -
multiple criteria decision making
Language(s) - English
Resource type - Journals
ISSN - 2084-1531
DOI - 10.22367/mcdm.2020.15.01
Subject(s) - computer science , lexicon , feature extraction , data mining , graph , knowledge graph , knowledge extraction , feature (linguistics) , pattern recognition (psychology) , key (lock) , domain (mathematical analysis) , artificial intelligence , relationship extraction , relation (database) , theoretical computer science , mathematics , mathematical analysis , linguistics , philosophy , computer security
In the field of text mining, many novel feature extraction approaches have been propounded. The following research paper is based on a novel feature extraction algorithm. In this paper, to formulate this approach, a weighted graph mining has been used to ensure the effectiveness of the feature extraction and computational efficiency; only the most effective graphs representing the maximum number of triangles based on a predefined relational criterion have been considered. The proposed novel technique is an amalgamation of the relation between words surrounding an aspect of the product and the lexicon-based connection among those words, which creates a relational triangle. A maximum number of a triangle covering an element has been accounted as a prime feature. The proposed algorithm performs more than three times better than TF-IDF within a limited set of data in analysis based on domain-specific data. Keywords: feature extraction, natural language processing, product review, text processing, knowledge graph.