RIEHAN: Relevant Information Enhanced Hierarchical Attention Network for Automated Claim Verification

Mingxuan Chen; Yupeng Cao; K. P. Subbalakshmi; Jingjing Dai

doi:10.1109/IMBDKM57416.2023.00022

RIEHAN: Relevant Information Enhanced Hierarchical Attention Network for Automated Claim Verification

Mingxuan Chen, Yupeng Cao, K. P. Subbalakshmi, Jingjing Dai

Department of Electrical and Computer Engineering

Stevens Institute of Technology

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

Abstract

The spread of misinformation in online media has caused significant societal problems today, underscoring the importance of verifying claims before accepting them as real. In this work, an automated claim verification module is designed, which is based on a hierarchical attention network. Latent features from the claim, latent features from all the articles that pertain to the claim, and the most relevant information feature extracted from the articles via a gating unit are utilized in this architecture. Ablation studies demonstrate that this trainable approach to extracting the most relevant information from articles performs better than the cosine similarity metric. We also demonstrate through ablation studies that improved performance metrics can be achieved by explicitly including the most pertinent information from articles in the model. The proposed model, Relevant Information Enhanced Hierarchical Attention Network (RIEHAN), performs best compared with the SOTA models on the PolitiFact database and the Snopes database.

Original language	English
Title of host publication	Proceedings - 2023 International Conference on Intelligent Media, Big Data and Knowledge Mining, IMBDKM 2023
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	84-88
Number of pages	5
ISBN (Electronic)	9781665492751
DOIs	https://doi.org/10.1109/IMBDKM57416.2023.00022
State	Published - 2023
Event	2023 International Conference on Intelligent Media, Big Data and Knowledge Mining, IMBDKM 2023 - Changsha, China Duration: Mar 17 2023 → Mar 19 2023

Publication series

Name	Proceedings - 2023 International Conference on Intelligent Media, Big Data and Knowledge Mining, IMBDKM 2023

Conference

Conference	2023 International Conference on Intelligent Media, Big Data and Knowledge Mining, IMBDKM 2023
Country/Territory	China
City	Changsha
Period	3/17/23 → 3/19/23

ASJC Scopus subject areas

Information Systems
Information Systems and Management
Media Technology
Artificial Intelligence
Computer Vision and Pattern Recognition

Keywords

Artificial Intelligence
Claim Verification
Data Mining
Deep Learning
Hierarchical Attention Network

Access to Document

10.1109/IMBDKM57416.2023.00022

Cite this

Chen, M., Cao, Y., Subbalakshmi, K. P., & Dai, J. (2023). RIEHAN: Relevant Information Enhanced Hierarchical Attention Network for Automated Claim Verification. In Proceedings - 2023 International Conference on Intelligent Media, Big Data and Knowledge Mining, IMBDKM 2023 (pp. 84-88). (Proceedings - 2023 International Conference on Intelligent Media, Big Data and Knowledge Mining, IMBDKM 2023). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/IMBDKM57416.2023.00022

Chen, Mingxuan ; Cao, Yupeng ; Subbalakshmi, K. P. et al. / RIEHAN : Relevant Information Enhanced Hierarchical Attention Network for Automated Claim Verification. Proceedings - 2023 International Conference on Intelligent Media, Big Data and Knowledge Mining, IMBDKM 2023. Institute of Electrical and Electronics Engineers Inc., 2023. pp. 84-88 (Proceedings - 2023 International Conference on Intelligent Media, Big Data and Knowledge Mining, IMBDKM 2023).

@inproceedings{6e25c48f5b42485d8be9a7b399dc841c,

title = "RIEHAN: Relevant Information Enhanced Hierarchical Attention Network for Automated Claim Verification",

abstract = "The spread of misinformation in online media has caused significant societal problems today, underscoring the importance of verifying claims before accepting them as real. In this work, an automated claim verification module is designed, which is based on a hierarchical attention network. Latent features from the claim, latent features from all the articles that pertain to the claim, and the most relevant information feature extracted from the articles via a gating unit are utilized in this architecture. Ablation studies demonstrate that this trainable approach to extracting the most relevant information from articles performs better than the cosine similarity metric. We also demonstrate through ablation studies that improved performance metrics can be achieved by explicitly including the most pertinent information from articles in the model. The proposed model, Relevant Information Enhanced Hierarchical Attention Network (RIEHAN), performs best compared with the SOTA models on the PolitiFact database and the Snopes database.",

keywords = "Artificial Intelligence, Claim Verification, Data Mining, Deep Learning, Hierarchical Attention Network",

author = "Mingxuan Chen and Yupeng Cao and Subbalakshmi, {K. P.} and Jingjing Dai",

note = "Publisher Copyright: {\textcopyright} 2023 IEEE.; 2023 International Conference on Intelligent Media, Big Data and Knowledge Mining, IMBDKM 2023 ; Conference date: 17-03-2023 Through 19-03-2023",

year = "2023",

doi = "10.1109/IMBDKM57416.2023.00022",

language = "English",

series = "Proceedings - 2023 International Conference on Intelligent Media, Big Data and Knowledge Mining, IMBDKM 2023",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

pages = "84--88",

booktitle = "Proceedings - 2023 International Conference on Intelligent Media, Big Data and Knowledge Mining, IMBDKM 2023",

}

Chen, M, Cao, Y, Subbalakshmi, KP & Dai, J 2023, RIEHAN: Relevant Information Enhanced Hierarchical Attention Network for Automated Claim Verification. in Proceedings - 2023 International Conference on Intelligent Media, Big Data and Knowledge Mining, IMBDKM 2023. Proceedings - 2023 International Conference on Intelligent Media, Big Data and Knowledge Mining, IMBDKM 2023, Institute of Electrical and Electronics Engineers Inc., pp. 84-88, 2023 International Conference on Intelligent Media, Big Data and Knowledge Mining, IMBDKM 2023, Changsha, China, 3/17/23. https://doi.org/10.1109/IMBDKM57416.2023.00022

RIEHAN: Relevant Information Enhanced Hierarchical Attention Network for Automated Claim Verification. / Chen, Mingxuan; Cao, Yupeng; Subbalakshmi, K. P. et al.
Proceedings - 2023 International Conference on Intelligent Media, Big Data and Knowledge Mining, IMBDKM 2023. Institute of Electrical and Electronics Engineers Inc., 2023. p. 84-88 (Proceedings - 2023 International Conference on Intelligent Media, Big Data and Knowledge Mining, IMBDKM 2023).

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

TY - GEN

T1 - RIEHAN

T2 - 2023 International Conference on Intelligent Media, Big Data and Knowledge Mining, IMBDKM 2023

AU - Chen, Mingxuan

AU - Cao, Yupeng

AU - Subbalakshmi, K. P.

AU - Dai, Jingjing

PY - 2023

Y1 - 2023

N2 - The spread of misinformation in online media has caused significant societal problems today, underscoring the importance of verifying claims before accepting them as real. In this work, an automated claim verification module is designed, which is based on a hierarchical attention network. Latent features from the claim, latent features from all the articles that pertain to the claim, and the most relevant information feature extracted from the articles via a gating unit are utilized in this architecture. Ablation studies demonstrate that this trainable approach to extracting the most relevant information from articles performs better than the cosine similarity metric. We also demonstrate through ablation studies that improved performance metrics can be achieved by explicitly including the most pertinent information from articles in the model. The proposed model, Relevant Information Enhanced Hierarchical Attention Network (RIEHAN), performs best compared with the SOTA models on the PolitiFact database and the Snopes database.

AB - The spread of misinformation in online media has caused significant societal problems today, underscoring the importance of verifying claims before accepting them as real. In this work, an automated claim verification module is designed, which is based on a hierarchical attention network. Latent features from the claim, latent features from all the articles that pertain to the claim, and the most relevant information feature extracted from the articles via a gating unit are utilized in this architecture. Ablation studies demonstrate that this trainable approach to extracting the most relevant information from articles performs better than the cosine similarity metric. We also demonstrate through ablation studies that improved performance metrics can be achieved by explicitly including the most pertinent information from articles in the model. The proposed model, Relevant Information Enhanced Hierarchical Attention Network (RIEHAN), performs best compared with the SOTA models on the PolitiFact database and the Snopes database.

KW - Artificial Intelligence

KW - Claim Verification

KW - Data Mining

KW - Deep Learning

KW - Hierarchical Attention Network

UR - http://www.scopus.com/inward/record.url?scp=85162876465&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85162876465&partnerID=8YFLogxK

U2 - 10.1109/IMBDKM57416.2023.00022

DO - 10.1109/IMBDKM57416.2023.00022

M3 - Conference contribution

T3 - Proceedings - 2023 International Conference on Intelligent Media, Big Data and Knowledge Mining, IMBDKM 2023

SP - 84

EP - 88

BT - Proceedings - 2023 International Conference on Intelligent Media, Big Data and Knowledge Mining, IMBDKM 2023

PB - Institute of Electrical and Electronics Engineers Inc.

Y2 - 17 March 2023 through 19 March 2023

ER -

Chen M, Cao Y, Subbalakshmi KP, Dai J. RIEHAN: Relevant Information Enhanced Hierarchical Attention Network for Automated Claim Verification. In Proceedings - 2023 International Conference on Intelligent Media, Big Data and Knowledge Mining, IMBDKM 2023. Institute of Electrical and Electronics Engineers Inc. 2023. p. 84-88. (Proceedings - 2023 International Conference on Intelligent Media, Big Data and Knowledge Mining, IMBDKM 2023). doi: 10.1109/IMBDKM57416.2023.00022

RIEHAN: Relevant Information Enhanced Hierarchical Attention Network for Automated Claim Verification

Abstract

Publication series

Conference

ASJC Scopus subject areas

Keywords

Access to Document

Other files and links

Fingerprint

Cite this