文章基本信息

标题：Aspect Extraction for Opinion Mining with aSemantic Model
本地全文：下载
作者：Carlos Henriquez ; German Sanchez-Torres
期刊名称：Engineering Letters
印刷版ISSN：1816-093X
电子版ISSN：1816-0948
出版年度：2021
卷号：29
期号：1
页码：61-67
语种：English
出版社：Newswood Ltd
摘要：In this article, we present a semantic modelfor aspect extraction from Spanish text as part of acomplete aspect-based sentiment analysis system. The modeluses ontology, semantic similarity, and double propagationtechniques to detect explicit and implicit aspects. The proposedapproach allows the implementation of a scalable system forany language or domain. The experimental tests were carriedout using the SemEval-2016 dataset for task 5, correspondingto the aspect-based sentiment analysis sentence level. Theimplemented system obtained an F1 score of 73.07 for theaspect extraction, achieving the best results among the systemsparticipating in the comparison, and an F1 score of 89.18 forthe hotel domain using a ten-iteration cross-validation.
关键词：Aspect-based sentiment analysis; ontology; opinion mining; natural language processing; semantic similarity