Sentiment classification for unlabeled dataset using Doc2vec with JST

Sangheon Lee; Xiangdan Jin; Wooju Kim

doi:10.1145/2971603.2971631

Sentiment classification for unlabeled dataset using Doc2vec with JST

Sangheon Lee, Xiangdan Jin, Wooju Kim

Department of Industrial Engineering

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

7 Citations (Scopus)

Abstract

Supervised learning require sentiment labeled corpus for training. But it is hard to apply automatic sentiment classification system to new domain because labeled dataset construction costs a lot of time. Meanwhile, researches using Doc2vec based document representation beat out other sentiment classification researches. However, these document representation methods only represent documents' context or sentiment. In this paper, we proposed supervised learning scheme for unlabeled corpus and also proposed document representation method which can simultaneously represent documents' context and sentiment.

Original language	English
Title of host publication	Proceedings of the 18th Annual International Conference on Electronic Commerce
Subtitle of host publication	e-Commerce in Smart connected World, ICEC 2016
Publisher	Association for Computing Machinery
ISBN (Electronic)	9781450342223
DOIs	https://doi.org/10.1145/2971603.2971631
Publication status	Published - 2016 Aug 17
Event	18th International Conference on Electronic Commerce, ICEC 2016 - Suwon, Korea, Republic of Duration: 2016 Aug 17 → 2016 Aug 19

Publication series

Name	ACM International Conference Proceeding Series
Volume	17-19-August-2016

Other

Other	18th International Conference on Electronic Commerce, ICEC 2016
Country/Territory	Korea, Republic of
City	Suwon
Period	16/8/17 → 16/8/19

Bibliographical note

Publisher Copyright:
Copyright is held by the owner/author(s).

All Science Journal Classification (ASJC) codes

Software
Human-Computer Interaction
Computer Vision and Pattern Recognition
Computer Networks and Communications

Access to Document

10.1145/2971603.2971631

Cite this

Lee, S., Jin, X., & Kim, W. (2016). Sentiment classification for unlabeled dataset using Doc2vec with JST. In Proceedings of the 18th Annual International Conference on Electronic Commerce: e-Commerce in Smart connected World, ICEC 2016 Article 2971631 (ACM International Conference Proceeding Series; Vol. 17-19-August-2016). Association for Computing Machinery. https://doi.org/10.1145/2971603.2971631

@inproceedings{d9da96d7681447c4973457ec919a2114,

title = "Sentiment classification for unlabeled dataset using Doc2vec with JST",

abstract = "Supervised learning require sentiment labeled corpus for training. But it is hard to apply automatic sentiment classification system to new domain because labeled dataset construction costs a lot of time. Meanwhile, researches using Doc2vec based document representation beat out other sentiment classification researches. However, these document representation methods only represent documents' context or sentiment. In this paper, we proposed supervised learning scheme for unlabeled corpus and also proposed document representation method which can simultaneously represent documents' context and sentiment.",

author = "Sangheon Lee and Xiangdan Jin and Wooju Kim",

note = "Publisher Copyright: Copyright is held by the owner/author(s).; 18th International Conference on Electronic Commerce, ICEC 2016 ; Conference date: 17-08-2016 Through 19-08-2016",

year = "2016",

month = aug,

day = "17",

doi = "10.1145/2971603.2971631",

language = "English",

series = "ACM International Conference Proceeding Series",

publisher = "Association for Computing Machinery",

booktitle = "Proceedings of the 18th Annual International Conference on Electronic Commerce",

}

Lee, S, Jin, X & Kim, W 2016, Sentiment classification for unlabeled dataset using Doc2vec with JST. in Proceedings of the 18th Annual International Conference on Electronic Commerce: e-Commerce in Smart connected World, ICEC 2016., 2971631, ACM International Conference Proceeding Series, vol. 17-19-August-2016, Association for Computing Machinery, 18th International Conference on Electronic Commerce, ICEC 2016, Suwon, Korea, Republic of, 16/8/17. https://doi.org/10.1145/2971603.2971631

Sentiment classification for unlabeled dataset using Doc2vec with JST. / Lee, Sangheon; Jin, Xiangdan; Kim, Wooju.
Proceedings of the 18th Annual International Conference on Electronic Commerce: e-Commerce in Smart connected World, ICEC 2016. Association for Computing Machinery, 2016. 2971631 (ACM International Conference Proceeding Series; Vol. 17-19-August-2016).

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

TY - GEN

T1 - Sentiment classification for unlabeled dataset using Doc2vec with JST

AU - Lee, Sangheon

AU - Jin, Xiangdan

AU - Kim, Wooju

N1 - Publisher Copyright: Copyright is held by the owner/author(s).

PY - 2016/8/17

Y1 - 2016/8/17

N2 - Supervised learning require sentiment labeled corpus for training. But it is hard to apply automatic sentiment classification system to new domain because labeled dataset construction costs a lot of time. Meanwhile, researches using Doc2vec based document representation beat out other sentiment classification researches. However, these document representation methods only represent documents' context or sentiment. In this paper, we proposed supervised learning scheme for unlabeled corpus and also proposed document representation method which can simultaneously represent documents' context and sentiment.

AB - Supervised learning require sentiment labeled corpus for training. But it is hard to apply automatic sentiment classification system to new domain because labeled dataset construction costs a lot of time. Meanwhile, researches using Doc2vec based document representation beat out other sentiment classification researches. However, these document representation methods only represent documents' context or sentiment. In this paper, we proposed supervised learning scheme for unlabeled corpus and also proposed document representation method which can simultaneously represent documents' context and sentiment.

UR - http://www.scopus.com/inward/record.url?scp=84988701335&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84988701335&partnerID=8YFLogxK

U2 - 10.1145/2971603.2971631

DO - 10.1145/2971603.2971631

M3 - Conference contribution

AN - SCOPUS:84988701335

T3 - ACM International Conference Proceeding Series

BT - Proceedings of the 18th Annual International Conference on Electronic Commerce

PB - Association for Computing Machinery

T2 - 18th International Conference on Electronic Commerce, ICEC 2016

Y2 - 17 August 2016 through 19 August 2016

ER -

Sentiment classification for unlabeled dataset using Doc2vec with JST

Abstract

Publication series

Other

Bibliographical note

All Science Journal Classification (ASJC) codes

Access to Document

Other files and links

Fingerprint

Cite this