Sentiment classification for unlabeled dataset using Doc2vec with JST

Sangheon Lee, Xiangdan Jin, Wooju Kim

Research output: Chapter in Book/Report/Conference proceedingConference contribution

3 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 languageEnglish
Title of host publicationProceedings of the 18th Annual International Conference on Electronic Commerce
Subtitle of host publicatione-Commerce in Smart connected World, ICEC 2016
PublisherAssociation for Computing Machinery
ISBN (Electronic)9781450342223
DOIs
Publication statusPublished - 2016 Aug 17
Event18th International Conference on Electronic Commerce, ICEC 2016 - Suwon, Korea, Republic of
Duration: 2016 Aug 172016 Aug 19

Publication series

NameACM International Conference Proceeding Series
Volume17-19-August-2016

Other

Other18th International Conference on Electronic Commerce, ICEC 2016
CountryKorea, Republic of
CitySuwon
Period16/8/1716/8/19

Fingerprint

Supervised learning
Costs

All Science Journal Classification (ASJC) codes

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

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 [2971631] (ACM International Conference Proceeding Series; Vol. 17-19-August-2016). Association for Computing Machinery. https://doi.org/10.1145/2971603.2971631
Lee, Sangheon ; Jin, Xiangdan ; Kim, Wooju. / Sentiment classification for unlabeled dataset using Doc2vec with JST. Proceedings of the 18th Annual International Conference on Electronic Commerce: e-Commerce in Smart connected World, ICEC 2016. Association for Computing Machinery, 2016. (ACM International Conference Proceeding Series).
@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",
year = "2016",
month = "8",
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 proceedingConference contribution

TY - GEN

T1 - Sentiment classification for unlabeled dataset using Doc2vec with JST

AU - Lee, Sangheon

AU - Jin, Xiangdan

AU - Kim, Wooju

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

ER -

Lee S, Jin X, Kim W. 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. Association for Computing Machinery. 2016. 2971631. (ACM International Conference Proceeding Series). https://doi.org/10.1145/2971603.2971631