skip to main content
10.1145/3397271.3401314acmconferencesArticle/Chapter ViewAbstractPublication PagesirConference Proceedingsconference-collections
short-paper

Multi-source Domain Adaptation for Sentiment Classification with Granger Causal Inference

Published: 25 July 2020 Publication History

Abstract

In this paper, we propose a multi-source domain adaptation method with a Granger-causal objective (MDA-GC) for cross-domain sentiment classification. Specifically, for each source domain, we build an expert model by using a novel sentiment-guided capsule network, which captures the domain invariant knowledge that bridges the knowledge gap between the source and target domains. Then, an attention mechanism is devised to assign importance weights to a mixture of experts, each of which specializes in a different source domain. In addition, we propose a Granger causal objective to make the weights assigned to individual experts correlate strongly with their contributions to the decision at hand. Experimental results on a benchmark dataset demonstrate that the proposed MDA-GC model significantly outperforms the compared methods.

References

[1]
John Blitzer, Mark Dredze, and Fernando Pereira. 2007. Biographies, bollywood, boom-boxes and blenders: Domain adaptation for sentiment classification. In ACL. 440--447.
[2]
Xavier Glorot and Yoshua Bengio. 2010. Understanding the difficulty of training deep feedforward neural networks. In AISTATS. 249--256.
[3]
Xavier Glorot, Antoine Bordes, and Yoshua Bengio. 2011. Domain adaptation for large-scale sentiment classification: A deep learning approach. In ICML. 513--520.
[4]
Clive WJ Granger. 1969. Investigating causal relations by econometric models and cross-spectral methods. Econometrica (1969), 424--438.
[5]
Jiang Guo, Darsh J Shah, and Regina Barzilay. 2018. Multi-source domain adaptation with mixture of experts. In EMNLP. 4694--4703.
[6]
Qingnan Jiang, Lei Chen, Ruifeng Xu, Xiang Ao, and Min Yang. 2019. A Challenge Dataset and Effective Models for Aspect-Based Sentiment Analysis. In EMNLP .
[7]
Sinno Jialin Pan, Xiaochuan Ni, Jian-Tao Sun, Qiang Yang, and Zheng Chen. 2010. Cross-domain sentiment classification via spectral feature alignment. In WWW .
[8]
Sara Sabour, Nicholas Frosst, and Geoffrey E Hinton. 2017. Dynamic routing between capsules. In NIPS. 3856--3866.
[9]
Patrick Schwab, Djordje Miladinovic, and Walter Karlen. 2019. Granger-causal attentive mixtures of experts: Learning important features with neural networks. In AAAI. 4846--4853.
[10]
Aliaksei Severyn and Alessandro Moschitti. 2015. Twitter sentiment analysis with deep convolutional neural networks. In SIGIR. 959--962.
[11]
Duyu Tang, Bing Qin, and Ting Liu. 2015. Document modeling with gated recurrent neural network for sentiment classification. In EMNLP. 1422--1432.
[12]
Theresa Wilson, Janyce Wiebe, and Paul Hoffmann. 2005. Recognizing contextual polarity in phrase-level sentiment analysis. In EMNLP. 347--354.
[13]
Fangzhao Wu and Yongfeng Huang. 2016. Sentiment domain adaptation with multiple sources. In ACL. 301--310.
[14]
Min Yang, Dingju Zhu, M Rashed, and Kam-Pui Chow. 2014. Learning domain-specific sentiment lexicon with supervised sentiment-aware LDA. ECAI (2014).
[15]
Han Zhao, Shanghang Zhang, Guanhang Wu, Geoffrey J Gordon, et al. 2018. Multiple source domain adaptation with adversarial learning. In ICLR Workshop.
[16]
Yftah Ziser and Roi Reichart. 2016. Neural structural correspondence learning for domain adaptation. arXiv preprint arXiv:1610.01588 (2016).
[17]
Yftah Ziser and Roi Reichart. 2018. Pivot Based Language Modeling for Improved Neural Domain Adaptation. In NAACL, Vol. 1. 1241--1251.

Cited By

View all
  • (2024)Learning with Asynchronous LabelsACM Transactions on Knowledge Discovery from Data10.1145/366218618:8(1-27)Online publication date: 3-May-2024
  • (2024)Enhancing cross-domain sentiment classification through multi-source collaborative training and selective ensemble methodsThe Journal of Supercomputing10.1007/s11227-024-06391-4Online publication date: 7-Aug-2024
  • (2024)Multi-Source Domain Adaptation for Emotion Classification Using Bi-LSTM and Broad LearningTextual Emotion Classification Using Deep Broad Learning10.1007/978-3-031-67718-2_6(99-117)Online publication date: 28-Sep-2024
  • Show More Cited By

Recommendations

Comments

Information & Contributors

Information

Published In

cover image ACM Conferences
SIGIR '20: Proceedings of the 43rd International ACM SIGIR Conference on Research and Development in Information Retrieval
July 2020
2548 pages
ISBN:9781450380164
DOI:10.1145/3397271
Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than ACM must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. Request permissions from [email protected]

Sponsors

Publisher

Association for Computing Machinery

New York, NY, United States

Publication History

Published: 25 July 2020

Permissions

Request permissions for this article.

Check for updates

Author Tags

  1. Granger causality
  2. capsule network
  3. domain adaptation
  4. multi-source domains
  5. sentiment classification

Qualifiers

  • Short-paper

Funding Sources

  • Natural Science Foundation of Guangdong Province of China
  • National Natural Science Foundation of China
  • Shenzhen Basic Research Foundation

Conference

SIGIR '20
Sponsor:

Acceptance Rates

Overall Acceptance Rate 792 of 3,983 submissions, 20%

Contributors

Other Metrics

Bibliometrics & Citations

Bibliometrics

Article Metrics

  • Downloads (Last 12 months)16
  • Downloads (Last 6 weeks)5
Reflects downloads up to 17 Feb 2025

Other Metrics

Citations

Cited By

View all
  • (2024)Learning with Asynchronous LabelsACM Transactions on Knowledge Discovery from Data10.1145/366218618:8(1-27)Online publication date: 3-May-2024
  • (2024)Enhancing cross-domain sentiment classification through multi-source collaborative training and selective ensemble methodsThe Journal of Supercomputing10.1007/s11227-024-06391-4Online publication date: 7-Aug-2024
  • (2024)Multi-Source Domain Adaptation for Emotion Classification Using Bi-LSTM and Broad LearningTextual Emotion Classification Using Deep Broad Learning10.1007/978-3-031-67718-2_6(99-117)Online publication date: 28-Sep-2024
  • (2022)Edge-Cloud Polarization and Collaboration: A Comprehensive Survey for AIIEEE Transactions on Knowledge and Data Engineering10.1109/TKDE.2022.3178211(1-1)Online publication date: 2022
  • (2022)A Cross-Domain Semantic Similarity Measure and Multi-Source Domain Adaptation in Sentiment Analysis2022 International Conference on Augmented Intelligence and Sustainable Systems (ICAISS)10.1109/ICAISS55157.2022.10011051(760-764)Online publication date: 24-Nov-2022
  • (2022)Contrastive transformer based domain adaptation for multi-source cross-domain sentiment classificationKnowledge-Based Systems10.1016/j.knosys.2022.108649245(108649)Online publication date: Jun-2022
  • (2021)Exploiting Domain-Aware Aspect Similarity for Multi-Source Cross-Domain Sentiment ClassificationAdvances in Science, Technology and Engineering Systems Journal10.25046/aj0604016:4(1-12)Online publication date: Jul-2021

View Options

Login options

View options

PDF

View or Download as a PDF file.

PDF

eReader

View online with eReader.

eReader

Figures

Tables

Media

Share

Share

Share this Publication link

Share on social media