Cross-domain sentiment classification using deep learning approach

Deep learning, as a new unsupervised leaning algorithm, has strong capabilities to learn data representations. Previous work has shown that new features learned by deep learning algorithm help to improve the accuracy of cross-domain classification. In this paper, we firstly propose a modified versio...

Full description

Saved in:
Bibliographic Details
Published in:IEEE ... International Conference on Cloud Computing and Intelligence Systems pp. 60 - 64
Main Authors: Miao Sun, Qi Tan, Runwei Ding, Hong Liu
Format: Conference Proceeding
Language:English
Published: IEEE 01.11.2014
Subjects:
Classification algorithms
Cross-domain
Deep learning
dimension reduction
feature augment
ISO standards
Noise reduction
Text sentiment classification
Training
ISBN:1479947202, 9781479947201
ISSN:2376-5933
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Abstract Deep learning, as a new unsupervised leaning algorithm, has strong capabilities to learn data representations. Previous work has shown that new features learned by deep learning algorithm help to improve the accuracy of cross-domain classification. In this paper, we firstly propose a modified version of marginalized stacked denoising autoencoders (mSDA). We call it mSDA++ algorithm, which can learn excellent and low-dimensional features for training classifier. In addition, we combine mSDA with EASYADAPT algorithm to further improve the accuracy of cross-domain classification. Then we use SVM, mSDA, mSDA++, and EA+mSDA algorithms to do the cross-domain sentiment classification experiments on Amazon benchmark dataset. The results show that EA+mSDA algorithm attains the best accuracy. Besides, the mSDA++ algorithm can accelerate the subsequent calculation and reduce the data storage space.
AbstractList Deep learning, as a new unsupervised leaning algorithm, has strong capabilities to learn data representations. Previous work has shown that new features learned by deep learning algorithm help to improve the accuracy of cross-domain classification. In this paper, we firstly propose a modified version of marginalized stacked denoising autoencoders (mSDA). We call it mSDA++ algorithm, which can learn excellent and low-dimensional features for training classifier. In addition, we combine mSDA with EASYADAPT algorithm to further improve the accuracy of cross-domain classification. Then we use SVM, mSDA, mSDA++, and EA+mSDA algorithms to do the cross-domain sentiment classification experiments on Amazon benchmark dataset. The results show that EA+mSDA algorithm attains the best accuracy. Besides, the mSDA++ algorithm can accelerate the subsequent calculation and reduce the data storage space.
Author Hong Liu
Qi Tan
Miao Sun
Runwei Ding
Author_xml – sequence: 1
  surname: Miao Sun
  fullname: Miao Sun
  email: sunmia0502@126.com
  organization: South China Nomal Univ., Guangzhou, China
– sequence: 2
  surname: Qi Tan
  fullname: Qi Tan
  email: tanqi@scnu.edu.cn
  organization: South China Nomal Univ., Guangzhou, China
– sequence: 3
  surname: Runwei Ding
  fullname: Runwei Ding
  email: dingrunwei@pkusz.edu.cn
  organization: Shenzhen Grad. Sch., Peking Univ., Shenzhen, China
– sequence: 4
  surname: Hong Liu
  fullname: Hong Liu
  email: hongliu@pku.edu.cn
  organization: Peking Univ., Beijing, China
BookMark eNo1j8tOwzAQRY0oEm3pByA2-YEUjx-xvYSIR6VKLIB1NXYmYJQ4URwW_D0gyuZcnc2Vzoot0pCIsUvgWwDurut697wVHNTWgNGGyxO2AmWcU0o6dfovRnCxYEshTVVqJ-U52-T8wTkHVzlhxZLd1tOQc9kMPcZUZEpz7H9QhA5zjm0MOMchFZ85preiIRqLjnBKv4bjOA0Y3i_YWYtdps1x1-z1_u6lfiz3Tw-7-mZfRsHtXAZqbVuFhhqnkLegpSMVvAZB6JA08IDWmkpYr6myHoz13oOSHDRRhXLNrv5-IxEdxin2OH0djv3yG5EYT4Q
ContentType Conference Proceeding
DBID 6IE
6IL
CBEJK
RIE
RIL
DOI 10.1109/CCIS.2014.7175703
DatabaseName IEEE Electronic Library (IEL) Conference Proceedings
IEEE Proceedings Order Plan All Online (POP All Online) 1998-present by volume
IEEE Xplore All Conference Proceedings
IEEE Xplore
IEEE Proceedings Order Plans (POP All) 1998-Present
DatabaseTitleList
Database_xml – sequence: 1
  dbid: RIE
  name: IEEE Xplore
  url: https://ieeexplore.ieee.org/
  sourceTypes: Publisher
DeliveryMethod fulltext_linktorsrc
Discipline Computer Science
EISBN 1479944394
9781479947195
1479947199
9781479944392
EndPage 64
ExternalDocumentID 7175703
Genre orig-research
GroupedDBID 6IE
6IF
6IK
6IL
6IN
AAJGR
AAWTH
ABLEC
ADZIZ
ALMA_UNASSIGNED_HOLDINGS
BEFXN
BFFAM
BGNUA
BKEBE
BPEOZ
CBEJK
CHZPO
IEGSK
IPLJI
M43
OCL
RIE
RIL
ID FETCH-LOGICAL-i208t-cef8f6cded94a0f1539e4cb512ea9ae510ca887628b5e68b178bbb143015ee6a3
IEDL.DBID RIE
ISBN 1479947202
9781479947201
ISICitedReferencesCount 4
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000392727800011&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN 2376-5933
IngestDate Wed Aug 27 02:04:48 EDT 2025
IsPeerReviewed false
IsScholarly false
Language English
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-i208t-cef8f6cded94a0f1539e4cb512ea9ae510ca887628b5e68b178bbb143015ee6a3
PageCount 5
ParticipantIDs ieee_primary_7175703
PublicationCentury 2000
PublicationDate 20141101
PublicationDateYYYYMMDD 2014-11-01
PublicationDate_xml – month: 11
  year: 2014
  text: 20141101
  day: 01
PublicationDecade 2010
PublicationTitle IEEE ... International Conference on Cloud Computing and Intelligence Systems
PublicationTitleAbbrev CCIS
PublicationYear 2014
Publisher IEEE
Publisher_xml – name: IEEE
SSID ssj0001969282
Score 1.5807551
Snippet Deep learning, as a new unsupervised leaning algorithm, has strong capabilities to learn data representations. Previous work has shown that new features...
SourceID ieee
SourceType Publisher
StartPage 60
SubjectTerms Classification algorithms
Cross-domain
Deep learning
dimension reduction
feature augment
ISO standards
Noise reduction
Text sentiment classification
Training
Title Cross-domain sentiment classification using deep learning approach
URI https://ieeexplore.ieee.org/document/7175703
WOSCitedRecordID wos000392727800011&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1NTwIxEJ0A8eAJFYzf6cGjhWXb3bZXNxK9EBI14Ub6MUs4uBAEfr9tWSAmXrxt99JmJu3MtPPeA3jkjCvBMPdlSYqUZ8ZSza2hPjxYnqWapWUSxSbEaCQnEzVuwNMBC4OIsfkMe-EzvuW7hd2Eq7K-Lz0CYVQTmkLkO6zW8T5F5SqN2lChz4NmvlCPOC6hFBe-wt_TO9XjQf3COUhUvyje3kOTF-_VE_xSWomBZtj-3xLPoHtE7JHxIRadQwOrC2jvJRtIvYM78FyEqEjd4kvPKxKAR5Hdn9iQRIeuoegoErrhZ8QhLkktKzEje_bxLnwOXz6KV1rLKNB5msg1tVjKMrcOneI6Kf0Rp9C7w0d6DNTcflNaLcOhKE2GuTQDIY0xPo_ymQJirtkltKpFhVdAnHNMZIpbpn0ZablMNEuUKXVpdVYKvIZOMMl0uWPKmNbWuPn79y2cBqvvkH130FqvNngPJ3a7nn-vHqJ7fwCgNaFJ
linkProvider IEEE
linkToHtml http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV3PT8IwFH5BNNETKhh_24NHC2PrtvbqIoGIhERMuJH-eCMcHATBv9-2DIiJF2_bLl360n7vte_7PoBHFjGRRpjYsiREymKlqWRaUQsPmsWhjMI88GYT6WDAx2MxrMDTjguDiL75DJvu0d_lm7leu6Oyli09nGDUARzGjIXBhq21P1ERiQi9O5Tr9KCxLdU9kysVgqW2xt8KPJXv7fKOsx2IVpb13l2bF2uWQ_zyWvFQ06n97ydPobHn7JHhDo3OoILFOdS2pg2kXMN1eM4cLlIz_5Szgjjqkdf3J9ql0a5vyIeKuH74KTGIC1IaS0zJVn-8AR-dl1HWpaWRAp2FAV9RjTnPE23QCCaD3G5yAm1ALNajE-e2y1JL7rZFrmJMuGqnXCllMymbKyAmMrqAajEv8BKIMSZKY8F0JG0hqRkPZBQIlctcyzhP8Qrqbkomi41WxqScjeu_Pz_AcXf01p_0e4PXGzhxEdjw_G6hulqu8Q6O9Pdq9rW896H-ATelpJA
openUrl ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=proceeding&rft.title=IEEE+...+International+Conference+on+Cloud+Computing+and+Intelligence+Systems&rft.atitle=Cross-domain+sentiment+classification+using+deep+learning+approach&rft.au=Miao+Sun&rft.au=Qi+Tan&rft.au=Runwei+Ding&rft.au=Hong+Liu&rft.date=2014-11-01&rft.pub=IEEE&rft.isbn=1479947202&rft.issn=2376-5933&rft.spage=60&rft.epage=64&rft_id=info:doi/10.1109%2FCCIS.2014.7175703&rft.externalDocID=7175703
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=2376-5933&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=2376-5933&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=2376-5933&client=summon