Semi-Supervised Target-Dependent Sentiment Classification for Micro-Blogs

The wealth of opinions expressed in micro-blogs, such as tweets, motivated researchers to develop techniques for automatic opinion detection. However, accuracies of such techniques are still limited. Moreover, current techniques focus on detecting sentiment polarity regardless of the topic (target)...

Descripción completa

Guardado en:
Detalles Bibliográficos
Autores principales: Abudalfa, Shadi I., Ahmed, Moataz A.
Formato: Articulo
Lenguaje:Inglés
Publicado: 2019
Materias:
Ciencias Informáticas
social opinions
sentiment analysis
target-dependent
polarity classification
semi- supervised learning
Acceso en línea:http://sedici.unlp.edu.ar/handle/10915/74462
Aporte de:
SEDICI (UNLP) de Universidad Nacional de La Plata
id I19-R120-10915-74462
record_format dspace
institution Universidad Nacional de La Plata
institution_str I-19
repository_str R-120
collection SEDICI (UNLP)
language Inglés
topic Ciencias Informáticas
social opinions
sentiment analysis
target-dependent
polarity classification
semi- supervised learning
spellingShingle Ciencias Informáticas
social opinions
sentiment analysis
target-dependent
polarity classification
semi- supervised learning
Abudalfa, Shadi I.
Ahmed, Moataz A.
Semi-Supervised Target-Dependent Sentiment Classification for Micro-Blogs
topic_facet Ciencias Informáticas
social opinions
sentiment analysis
target-dependent
polarity classification
semi- supervised learning
description The wealth of opinions expressed in micro-blogs, such as tweets, motivated researchers to develop techniques for automatic opinion detection. However, accuracies of such techniques are still limited. Moreover, current techniques focus on detecting sentiment polarity regardless of the topic (target) discussed. Detecting sentiment towards a specific target, referred to as target-dependent sentiment classification, has not received adequate researchers’ attention. Literature review has shown that all target-dependent approaches use supervised learning techniques. Such techniques need a large number of labeled data. However, labeling data in social media is cumbersome and error prone. The research presented in this paper addresses this issue by employing semi-supervised learning techniques for target-dependent sentiment classification. Semisupervised learning techniques make use of labeled as well as unlabeled data. In this paper, we present a new semi-supervised learning technique that uses less number of labeled micro-blogs than that used by supervised learning techniques. Experiment results have shown that the proposed technique provides comparable accuracy.
format Articulo
Articulo
author Abudalfa, Shadi I.
Ahmed, Moataz A.
author_facet Abudalfa, Shadi I.
Ahmed, Moataz A.
author_sort Abudalfa, Shadi I.
title Semi-Supervised Target-Dependent Sentiment Classification for Micro-Blogs
title_short Semi-Supervised Target-Dependent Sentiment Classification for Micro-Blogs
title_full Semi-Supervised Target-Dependent Sentiment Classification for Micro-Blogs
title_fullStr Semi-Supervised Target-Dependent Sentiment Classification for Micro-Blogs
title_full_unstemmed Semi-Supervised Target-Dependent Sentiment Classification for Micro-Blogs
title_sort semi-supervised target-dependent sentiment classification for micro-blogs
publishDate 2019
url http://sedici.unlp.edu.ar/handle/10915/74462
work_keys_str_mv AT abudalfashadii semisupervisedtargetdependentsentimentclassificationformicroblogs
AT ahmedmoataza semisupervisedtargetdependentsentimentclassificationformicroblogs
AT abudalfashadii clasificaciondesentimientossemisupervisadaydependientedeobjetivoparamicroblogs
AT ahmedmoataza clasificaciondesentimientossemisupervisadaydependientedeobjetivoparamicroblogs
bdutipo_str Repositorios
_version_ 1764820483723755523

Ejemplares similares