Japanese sentiment analysis using simple alignment sentence classification

Hirotaka Niitsuma; Daiki Kubota; Manabu Ohta

doi:10.1145/3281375.3281388

Japanese sentiment analysis using simple alignment sentence classification

Hirotaka Niitsuma, Daiki Kubota, Manabu Ohta

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Abstract

Recurrent and convolutional neural networks have been used to learn contextual information in many natural-language processing studies. In particular, they are the most successful methods for English-language text analysis. In the sentiment analysis of English-language text, recurrent neural networks with an attention mechanism have been found to perform well. We might assume that context would be less important in Japanese-language sentiment analysis. To examine this assumption, we apply a simple alignment sentence-classification model to Japanese sentiment analysis.

Original language	English
Title of host publication	MEDES 2018 - 10th International Conference on Management of Digital EcoSystems
Publisher	Association for Computing Machinery, Inc
Pages	126-131
Number of pages	6
ISBN (Electronic)	9781450356220
DOIs	https://doi.org/10.1145/3281375.3281388
Publication status	Published - Sept 25 2018
Event	10th International Conference on Management of Digital EcoSystems, MEDES 2018 - Tokyo, Japan Duration: Sept 25 2018 → Sept 28 2018

Other

Other	10th International Conference on Management of Digital EcoSystems, MEDES 2018
Country/Territory	Japan
City	Tokyo
Period	9/25/18 → 9/28/18

Keywords

Aspect-based sentiment analysis
Japanese sentiment analysis
Word2vec

ASJC Scopus subject areas

Computer Graphics and Computer-Aided Design
Computer Networks and Communications
Environmental Engineering

Access to Document

10.1145/3281375.3281388

Cite this

Niitsuma, H, Kubota, D & Ohta, M 2018, Japanese sentiment analysis using simple alignment sentence classification. in MEDES 2018 - 10th International Conference on Management of Digital EcoSystems. Association for Computing Machinery, Inc, pp. 126-131, 10th International Conference on Management of Digital EcoSystems, MEDES 2018, Tokyo, Japan, 9/25/18. https://doi.org/10.1145/3281375.3281388

@inproceedings{2581bb3e7a3946ecb3018f5d4920cc2b,

title = "Japanese sentiment analysis using simple alignment sentence classification",

abstract = "Recurrent and convolutional neural networks have been used to learn contextual information in many natural-language processing studies. In particular, they are the most successful methods for English-language text analysis. In the sentiment analysis of English-language text, recurrent neural networks with an attention mechanism have been found to perform well. We might assume that context would be less important in Japanese-language sentiment analysis. To examine this assumption, we apply a simple alignment sentence-classification model to Japanese sentiment analysis.",

keywords = "Aspect-based sentiment analysis, Japanese sentiment analysis, Word2vec",

author = "Hirotaka Niitsuma and Daiki Kubota and Manabu Ohta",

year = "2018",

month = sep,

day = "25",

doi = "10.1145/3281375.3281388",

language = "English",

pages = "126--131",

booktitle = "MEDES 2018 - 10th International Conference on Management of Digital EcoSystems",

publisher = "Association for Computing Machinery, Inc",

note = "10th International Conference on Management of Digital EcoSystems, MEDES 2018 ; Conference date: 25-09-2018 Through 28-09-2018",

}

TY - GEN

T1 - Japanese sentiment analysis using simple alignment sentence classification

AU - Niitsuma, Hirotaka

AU - Kubota, Daiki

AU - Ohta, Manabu

PY - 2018/9/25

Y1 - 2018/9/25

N2 - Recurrent and convolutional neural networks have been used to learn contextual information in many natural-language processing studies. In particular, they are the most successful methods for English-language text analysis. In the sentiment analysis of English-language text, recurrent neural networks with an attention mechanism have been found to perform well. We might assume that context would be less important in Japanese-language sentiment analysis. To examine this assumption, we apply a simple alignment sentence-classification model to Japanese sentiment analysis.

AB - Recurrent and convolutional neural networks have been used to learn contextual information in many natural-language processing studies. In particular, they are the most successful methods for English-language text analysis. In the sentiment analysis of English-language text, recurrent neural networks with an attention mechanism have been found to perform well. We might assume that context would be less important in Japanese-language sentiment analysis. To examine this assumption, we apply a simple alignment sentence-classification model to Japanese sentiment analysis.

KW - Aspect-based sentiment analysis

KW - Japanese sentiment analysis

KW - Word2vec

UR - http://www.scopus.com/inward/record.url?scp=85058635807&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85058635807&partnerID=8YFLogxK

U2 - 10.1145/3281375.3281388

DO - 10.1145/3281375.3281388

M3 - Conference contribution

AN - SCOPUS:85058635807

SP - 126

EP - 131

BT - MEDES 2018 - 10th International Conference on Management of Digital EcoSystems

PB - Association for Computing Machinery, Inc

T2 - 10th International Conference on Management of Digital EcoSystems, MEDES 2018

Y2 - 25 September 2018 through 28 September 2018

ER -

Japanese sentiment analysis using simple alignment sentence classification

Abstract

Other

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this