IEICE TRANSACTIONS on Information
Heterogeneous Graph Contrastive Learning for Stance Prediction
Summary :
Stance prediction on social media aims to infer the stances of users towards a specific topic or event, which are not expressed explicitly. It is of great significance for public opinion analysis to extract and determine users' stances using user-generated content on social media. Existing research makes use of various signals, ranging from text content to online network connections of users on these platforms. However, it lacks joint modeling of the heterogeneous information for stance prediction. In this paper, we propose a self-supervised heterogeneous graph contrastive learning framework for stance prediction in online debate forums. Firstly, we perform data augmentation on the original heterogeneous information network to generate an augmented view. The original view and augmented view are learned from a meta-path based graph encoder respectively. Then, the contrastive learning among the two views is conducted to obtain high-quality representations of users and issues. Finally, the stance prediction is accomplished by matrix factorization between users and issues. The experimental results on an online debate forum dataset show that our model outperforms other competitive baseline methods significantly.
- Publication
- IEICE TRANSACTIONS on Information Vol.E105-D No.10 pp.1790-1798
- Publication Date
- 2022/10/01
- Publicized
- 2022/07/25
- Online ISSN
- 1745-1361
- DOI
- 10.1587/transinf.2022EDP7065
- Type of Manuscript
- PAPER
- Category
- Natural Language Processing
Authors
Keyword
Latest Issue
Copyrights notice of machine-translated contents
The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
Cite this
Copy
Yang LI, Rui QI, "Heterogeneous Graph Contrastive Learning for Stance Prediction" in IEICE TRANSACTIONS on Information,
vol. E105-D, no. 10, pp. 1790-1798, October 2022, doi: 10.1587/transinf.2022EDP7065.
Abstract: Stance prediction on social media aims to infer the stances of users towards a specific topic or event, which are not expressed explicitly. It is of great significance for public opinion analysis to extract and determine users' stances using user-generated content on social media. Existing research makes use of various signals, ranging from text content to online network connections of users on these platforms. However, it lacks joint modeling of the heterogeneous information for stance prediction. In this paper, we propose a self-supervised heterogeneous graph contrastive learning framework for stance prediction in online debate forums. Firstly, we perform data augmentation on the original heterogeneous information network to generate an augmented view. The original view and augmented view are learned from a meta-path based graph encoder respectively. Then, the contrastive learning among the two views is conducted to obtain high-quality representations of users and issues. Finally, the stance prediction is accomplished by matrix factorization between users and issues. The experimental results on an online debate forum dataset show that our model outperforms other competitive baseline methods significantly.
URL: https://global.ieice.org/en_transactions/information/10.1587/transinf.2022EDP7065/_p
Copy
@ARTICLE{e105-d_10_1790,
author={Yang LI, Rui QI, },
journal={IEICE TRANSACTIONS on Information},
title={Heterogeneous Graph Contrastive Learning for Stance Prediction},
year={2022},
volume={E105-D},
number={10},
pages={1790-1798},
abstract={Stance prediction on social media aims to infer the stances of users towards a specific topic or event, which are not expressed explicitly. It is of great significance for public opinion analysis to extract and determine users' stances using user-generated content on social media. Existing research makes use of various signals, ranging from text content to online network connections of users on these platforms. However, it lacks joint modeling of the heterogeneous information for stance prediction. In this paper, we propose a self-supervised heterogeneous graph contrastive learning framework for stance prediction in online debate forums. Firstly, we perform data augmentation on the original heterogeneous information network to generate an augmented view. The original view and augmented view are learned from a meta-path based graph encoder respectively. Then, the contrastive learning among the two views is conducted to obtain high-quality representations of users and issues. Finally, the stance prediction is accomplished by matrix factorization between users and issues. The experimental results on an online debate forum dataset show that our model outperforms other competitive baseline methods significantly.},
keywords={},
doi={10.1587/transinf.2022EDP7065},
ISSN={1745-1361},
month={October},}
Copy
TY - JOUR
TI - Heterogeneous Graph Contrastive Learning for Stance Prediction
T2 - IEICE TRANSACTIONS on Information
SP - 1790
EP - 1798
AU - Yang LI
AU - Rui QI
PY - 2022
DO - 10.1587/transinf.2022EDP7065
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E105-D
IS - 10
JA - IEICE TRANSACTIONS on Information
Y1 - October 2022
AB - Stance prediction on social media aims to infer the stances of users towards a specific topic or event, which are not expressed explicitly. It is of great significance for public opinion analysis to extract and determine users' stances using user-generated content on social media. Existing research makes use of various signals, ranging from text content to online network connections of users on these platforms. However, it lacks joint modeling of the heterogeneous information for stance prediction. In this paper, we propose a self-supervised heterogeneous graph contrastive learning framework for stance prediction in online debate forums. Firstly, we perform data augmentation on the original heterogeneous information network to generate an augmented view. The original view and augmented view are learned from a meta-path based graph encoder respectively. Then, the contrastive learning among the two views is conducted to obtain high-quality representations of users and issues. Finally, the stance prediction is accomplished by matrix factorization between users and issues. The experimental results on an online debate forum dataset show that our model outperforms other competitive baseline methods significantly.
ER -
English
