A Trustworthy Approach to Classify and Analyze Epidemic-Related Information From Microblogs

Research output: Contribution to journalArticleResearchpeer review

Authors

Research Organisations

External Research Organisations

  • Indian Institute of Technology Kharagpur (IITKGP)
View graph of relations

Details

Original languageEnglish
Pages (from-to)1-13
Number of pages13
JournalIEEE Transactions on Computational Social Systems
Early online date13 May 2024
Publication statusE-pub ahead of print - 13 May 2024

Abstract

Social media platforms, such as Twitter, are crucial resources to obtain situational information during disease outbreaks. Due to the sheer volume of user-generated content, providing tools that can automatically classify input texts into various types, such as symptoms, transmission, prevention measures, etc., and generate concise situational updates is necessary. Apart from high classification accuracy, interpretability is an important requirement when designing machine learning models for tasks in medical domain. In this article, we provide annotated epidemic-related datasets with labels of information types and rationales, which are short phrases from the original tweets, to support the assigned labels. Next, we introduce a trustworthy approach for the automatic classification of tweets posted during epidemics. Our classification model is able to extract short explanations/rationales for output decisions on unseen data. Moreover, we propose a simple graph-based ranking method to generate short summaries of tweets. Experiments on two epidemic-related datasets show the following: 1) our classification model obtains an average of 82% Macro-F1 and better interpretability scores in terms of Token-F1 (20% improvement) than baselines; 2) the extracted rationales capture essential disease-related information in the tweets; 3) our graph-based method with rationales is simple, yet efficient for generating concise situational updates.

Keywords

    Blogs, Classification, Computational modeling, Data mining, Diseases, epidemic, Feature extraction, health crisis, microblogs, Social networking (online), Transformers, trustworthy systems

ASJC Scopus subject areas

Sustainable Development Goals

Cite this

A Trustworthy Approach to Classify and Analyze Epidemic-Related Information From Microblogs. / Nguyen, Thi Huyen; Fisichella, Marco; Rudra, Koustav.
In: IEEE Transactions on Computational Social Systems, 13.05.2024, p. 1-13.

Research output: Contribution to journalArticleResearchpeer review

Nguyen, T. H., Fisichella, M., & Rudra, K. (2024). A Trustworthy Approach to Classify and Analyze Epidemic-Related Information From Microblogs. IEEE Transactions on Computational Social Systems, 1-13. Advance online publication. https://doi.org/10.1109/TCSS.2024.3391395
Nguyen TH, Fisichella M, Rudra K. A Trustworthy Approach to Classify and Analyze Epidemic-Related Information From Microblogs. IEEE Transactions on Computational Social Systems. 2024 May 13;1-13. Epub 2024 May 13. doi: 10.1109/TCSS.2024.3391395
Nguyen, Thi Huyen ; Fisichella, Marco ; Rudra, Koustav. / A Trustworthy Approach to Classify and Analyze Epidemic-Related Information From Microblogs. In: IEEE Transactions on Computational Social Systems. 2024 ; pp. 1-13.
Download
@article{af2b8ef7075c4f3980446fc7af14cbd0,
title = "A Trustworthy Approach to Classify and Analyze Epidemic-Related Information From Microblogs",
abstract = "Social media platforms, such as Twitter, are crucial resources to obtain situational information during disease outbreaks. Due to the sheer volume of user-generated content, providing tools that can automatically classify input texts into various types, such as symptoms, transmission, prevention measures, etc., and generate concise situational updates is necessary. Apart from high classification accuracy, interpretability is an important requirement when designing machine learning models for tasks in medical domain. In this article, we provide annotated epidemic-related datasets with labels of information types and rationales, which are short phrases from the original tweets, to support the assigned labels. Next, we introduce a trustworthy approach for the automatic classification of tweets posted during epidemics. Our classification model is able to extract short explanations/rationales for output decisions on unseen data. Moreover, we propose a simple graph-based ranking method to generate short summaries of tweets. Experiments on two epidemic-related datasets show the following: 1) our classification model obtains an average of 82% Macro-F1 and better interpretability scores in terms of Token-F1 (20% improvement) than baselines; 2) the extracted rationales capture essential disease-related information in the tweets; 3) our graph-based method with rationales is simple, yet efficient for generating concise situational updates.",
keywords = "Blogs, Classification, Computational modeling, Data mining, Diseases, epidemic, Feature extraction, health crisis, microblogs, Social networking (online), Transformers, trustworthy systems",
author = "Nguyen, {Thi Huyen} and Marco Fisichella and Koustav Rudra",
note = "Publisher Copyright: IEEE",
year = "2024",
month = may,
day = "13",
doi = "10.1109/TCSS.2024.3391395",
language = "English",
pages = "1--13",

}

Download

TY - JOUR

T1 - A Trustworthy Approach to Classify and Analyze Epidemic-Related Information From Microblogs

AU - Nguyen, Thi Huyen

AU - Fisichella, Marco

AU - Rudra, Koustav

N1 - Publisher Copyright: IEEE

PY - 2024/5/13

Y1 - 2024/5/13

N2 - Social media platforms, such as Twitter, are crucial resources to obtain situational information during disease outbreaks. Due to the sheer volume of user-generated content, providing tools that can automatically classify input texts into various types, such as symptoms, transmission, prevention measures, etc., and generate concise situational updates is necessary. Apart from high classification accuracy, interpretability is an important requirement when designing machine learning models for tasks in medical domain. In this article, we provide annotated epidemic-related datasets with labels of information types and rationales, which are short phrases from the original tweets, to support the assigned labels. Next, we introduce a trustworthy approach for the automatic classification of tweets posted during epidemics. Our classification model is able to extract short explanations/rationales for output decisions on unseen data. Moreover, we propose a simple graph-based ranking method to generate short summaries of tweets. Experiments on two epidemic-related datasets show the following: 1) our classification model obtains an average of 82% Macro-F1 and better interpretability scores in terms of Token-F1 (20% improvement) than baselines; 2) the extracted rationales capture essential disease-related information in the tweets; 3) our graph-based method with rationales is simple, yet efficient for generating concise situational updates.

AB - Social media platforms, such as Twitter, are crucial resources to obtain situational information during disease outbreaks. Due to the sheer volume of user-generated content, providing tools that can automatically classify input texts into various types, such as symptoms, transmission, prevention measures, etc., and generate concise situational updates is necessary. Apart from high classification accuracy, interpretability is an important requirement when designing machine learning models for tasks in medical domain. In this article, we provide annotated epidemic-related datasets with labels of information types and rationales, which are short phrases from the original tweets, to support the assigned labels. Next, we introduce a trustworthy approach for the automatic classification of tweets posted during epidemics. Our classification model is able to extract short explanations/rationales for output decisions on unseen data. Moreover, we propose a simple graph-based ranking method to generate short summaries of tweets. Experiments on two epidemic-related datasets show the following: 1) our classification model obtains an average of 82% Macro-F1 and better interpretability scores in terms of Token-F1 (20% improvement) than baselines; 2) the extracted rationales capture essential disease-related information in the tweets; 3) our graph-based method with rationales is simple, yet efficient for generating concise situational updates.

KW - Blogs

KW - Classification

KW - Computational modeling

KW - Data mining

KW - Diseases

KW - epidemic

KW - Feature extraction

KW - health crisis

KW - microblogs

KW - Social networking (online)

KW - Transformers

KW - trustworthy systems

UR - http://www.scopus.com/inward/record.url?scp=85193299864&partnerID=8YFLogxK

U2 - 10.1109/TCSS.2024.3391395

DO - 10.1109/TCSS.2024.3391395

M3 - Article

AN - SCOPUS:85193299864

SP - 1

EP - 13

JO - IEEE Transactions on Computational Social Systems

JF - IEEE Transactions on Computational Social Systems

ER -

By the same author(s)