Cargando…

Automatic Construction and Global Optimization of a Multisentiment Lexicon

Manual annotation of sentiment lexicons costs too much labor and time, and it is also difficult to get accurate quantification of emotional intensity. Besides, the excessive emphasis on one specific field has greatly limited the applicability of domain sentiment lexicons (Wang et al., 2010). This pa...

Descripción completa

Detalles Bibliográficos
Autores principales: Yang, Xiaoping, Zhang, Zhongxia, Zhang, Zhongqiu, Mo, Yuting, Li, Lianbei, Yu, Li, Zhu, Peican
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Hindawi Publishing Corporation 2016
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC5153545/
https://www.ncbi.nlm.nih.gov/pubmed/28042290
http://dx.doi.org/10.1155/2016/2093406
_version_ 1782474713996460032
author Yang, Xiaoping
Zhang, Zhongxia
Zhang, Zhongqiu
Mo, Yuting
Li, Lianbei
Yu, Li
Zhu, Peican
author_facet Yang, Xiaoping
Zhang, Zhongxia
Zhang, Zhongqiu
Mo, Yuting
Li, Lianbei
Yu, Li
Zhu, Peican
author_sort Yang, Xiaoping
collection PubMed
description Manual annotation of sentiment lexicons costs too much labor and time, and it is also difficult to get accurate quantification of emotional intensity. Besides, the excessive emphasis on one specific field has greatly limited the applicability of domain sentiment lexicons (Wang et al., 2010). This paper implements statistical training for large-scale Chinese corpus through neural network language model and proposes an automatic method of constructing a multidimensional sentiment lexicon based on constraints of coordinate offset. In order to distinguish the sentiment polarities of those words which may express either positive or negative meanings in different contexts, we further present a sentiment disambiguation algorithm to increase the flexibility of our lexicon. Lastly, we present a global optimization framework that provides a unified way to combine several human-annotated resources for learning our 10-dimensional sentiment lexicon SentiRuc. Experiments show the superior performance of SentiRuc lexicon in category labeling test, intensity labeling test, and sentiment classification tasks. It is worth mentioning that, in intensity label test, SentiRuc outperforms the second place by 21 percent.
format Online
Article
Text
id pubmed-5153545
institution National Center for Biotechnology Information
language English
publishDate 2016
publisher Hindawi Publishing Corporation
record_format MEDLINE/PubMed
spelling pubmed-51535452017-01-01 Automatic Construction and Global Optimization of a Multisentiment Lexicon Yang, Xiaoping Zhang, Zhongxia Zhang, Zhongqiu Mo, Yuting Li, Lianbei Yu, Li Zhu, Peican Comput Intell Neurosci Research Article Manual annotation of sentiment lexicons costs too much labor and time, and it is also difficult to get accurate quantification of emotional intensity. Besides, the excessive emphasis on one specific field has greatly limited the applicability of domain sentiment lexicons (Wang et al., 2010). This paper implements statistical training for large-scale Chinese corpus through neural network language model and proposes an automatic method of constructing a multidimensional sentiment lexicon based on constraints of coordinate offset. In order to distinguish the sentiment polarities of those words which may express either positive or negative meanings in different contexts, we further present a sentiment disambiguation algorithm to increase the flexibility of our lexicon. Lastly, we present a global optimization framework that provides a unified way to combine several human-annotated resources for learning our 10-dimensional sentiment lexicon SentiRuc. Experiments show the superior performance of SentiRuc lexicon in category labeling test, intensity labeling test, and sentiment classification tasks. It is worth mentioning that, in intensity label test, SentiRuc outperforms the second place by 21 percent. Hindawi Publishing Corporation 2016 2016-11-29 /pmc/articles/PMC5153545/ /pubmed/28042290 http://dx.doi.org/10.1155/2016/2093406 Text en Copyright © 2016 Xiaoping Yang et al. https://creativecommons.org/licenses/by/4.0/ This is an open access article distributed under the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
spellingShingle Research Article
Yang, Xiaoping
Zhang, Zhongxia
Zhang, Zhongqiu
Mo, Yuting
Li, Lianbei
Yu, Li
Zhu, Peican
Automatic Construction and Global Optimization of a Multisentiment Lexicon
title Automatic Construction and Global Optimization of a Multisentiment Lexicon
title_full Automatic Construction and Global Optimization of a Multisentiment Lexicon
title_fullStr Automatic Construction and Global Optimization of a Multisentiment Lexicon
title_full_unstemmed Automatic Construction and Global Optimization of a Multisentiment Lexicon
title_short Automatic Construction and Global Optimization of a Multisentiment Lexicon
title_sort automatic construction and global optimization of a multisentiment lexicon
topic Research Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC5153545/
https://www.ncbi.nlm.nih.gov/pubmed/28042290
http://dx.doi.org/10.1155/2016/2093406
work_keys_str_mv AT yangxiaoping automaticconstructionandglobaloptimizationofamultisentimentlexicon
AT zhangzhongxia automaticconstructionandglobaloptimizationofamultisentimentlexicon
AT zhangzhongqiu automaticconstructionandglobaloptimizationofamultisentimentlexicon
AT moyuting automaticconstructionandglobaloptimizationofamultisentimentlexicon
AT lilianbei automaticconstructionandglobaloptimizationofamultisentimentlexicon
AT yuli automaticconstructionandglobaloptimizationofamultisentimentlexicon
AT zhupeican automaticconstructionandglobaloptimizationofamultisentimentlexicon