Mapping Crisp Structural Semantic Similarity Measures to Fuzzy Context: A Generic Approach

Ontology-based similarity measures have received much importance in recent years. In many real-world cases, the domain considered in the ontological similarity assessment consists of uncertainty or incomplete information. Such vagueness has led to the successful implementation of fuzzy ontology (FO)...

Full description

Saved in:
Bibliographic Details
Published in:International journal of fuzzy systems 2020-06, Vol.22 (4), p.1224-1242
Main Authors: Safaeipour, Hoda, Fazel Zarandi, M. H., Bastani, Susan
Format: Article
Language:English
Subjects:
Algorithms
Artificial Intelligence
Computational Intelligence
Context
Engineering
Fuzzy logic
Fuzzy sets
Image retrieval
Information retrieval
Management Science
Mapping
Ontology
Operations Research
Recommender systems
Reputation management
Semantic web
Semantics
Similarity
Similarity measures
Taxonomy
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Ontology-based similarity measures have received much importance in recent years. In many real-world cases, the domain considered in the ontological similarity assessment consists of uncertainty or incomplete information. Such vagueness has led to the successful implementation of fuzzy ontology (FO)-based similarity measures. Despite various applications of FO-based similarity measures, limited methods have so far been proposed for this purpose. Accordingly, this paper presents a generic model for semantic similarity assessment based on a fuzzy ontology. The proposed approach relies on the broad literature of Crisp Ontology-based Structural Semantic Similarity Measures (CO-SSSM). It provides an approach for mapping CO-SSSMs to fuzzy context. Consequently, the proposed generic model can be applied to various CO-SSSMs to develop their corresponding FO-SSSMs. In this regard, as an empirical investigation, four of the common CO-SSSMs were selected, their equivalent FO-SSSMs were developed by means of the proposed approach, and the accuracy of their similarity assessment was compared with each other. The results show the power of FO-SSSMs in describing the relations between concepts and their superiority over CO-SSSMs.
ISSN:1562-2479
2199-3211
DOI:10.1007/s40815-020-00833-w