Ontology enrichment from opinions using machine learning algorithms

Systems based on ontologies enable better data exploitation and provide credible and contextualized knowledge. Several sources of knowledge have been explored for developing and refining ontologies. Nonetheless, creating and enriching ontologies by exploiting the opinions’ characteristics is unexplo...

Full description

Saved in:
Bibliographic Details
Published in:International journal of information technology (Singapore. Online) 2024, Vol.16 (8), p.4941-4951
Main Authors: Oussaid, Melissa, Bouarab-Dahmani, Farida
Format: Article
Language:English
Subjects:
Artificial Intelligence
Computer Imaging
Computer Science
Image Processing and Computer Vision
Machine Learning
Original Research
Pattern Recognition and Graphics
Software Engineering
Vision
Citations: Items that this one cites
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Systems based on ontologies enable better data exploitation and provide credible and contextualized knowledge. Several sources of knowledge have been explored for developing and refining ontologies. Nonetheless, creating and enriching ontologies by exploiting the opinions’ characteristics is unexplored. This study introduces a new method for ontology learning based on users' opinions mining (OM). Our approach combines machine learning (ML), deep learning (DL), and natural language processing (NLP) techniques for opinion mining. It involves analyzing customers’ opinions to extract opinion features (category, aspect, opinion term) to generate new concepts, properties, and domain values of properties suitable for enriching a domain ontology. We evaluated the proposed method by applying it to the food industry domain, which is particularly sensitive to human opinion, using the FoodyM ontology and a food opinion corpus. The obtained results are promising, with a precision of 95.45% and F-measure of 97.67%, which offers new perspectives for improving food management by exploiting consumers’ opinions.
ISSN:2511-2104
2511-2112
DOI:10.1007/s41870-024-01873-3