Exploring Spillover Effects for COVID-19 Cascade Prediction
An information outbreak occurs on social media along with the COVID-19 pandemic and leads to an <i>infodemic</i>. Predicting the popularity of online content, known as <i>cascade prediction</i>, allows for not only catching in advance information that deserves attention, but...
Main Authors: | , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2022-01-01
|
Series: | Entropy |
Subjects: | |
Online Access: | https://www.mdpi.com/1099-4300/24/2/222 |
_version_ | 1797480572817244160 |
---|---|
author | Ninghan Chen Xihui Chen Zhiqiang Zhong Jun Pang |
author_facet | Ninghan Chen Xihui Chen Zhiqiang Zhong Jun Pang |
author_sort | Ninghan Chen |
collection | DOAJ |
description | An information outbreak occurs on social media along with the COVID-19 pandemic and leads to an <i>infodemic</i>. Predicting the popularity of online content, known as <i>cascade prediction</i>, allows for not only catching in advance information that deserves attention, but also identifying false information that will widely spread and require quick response to mitigate its negative impact. Among the various information diffusion patterns leveraged in previous works, the <i>spillover effect</i> of the information exposed to users on their decisions to participate in diffusing certain information has not been studied. In this paper, we focus on the diffusion of information related to COVID-19 preventive measures due to its special role in consolidating public efforts to slow down the spread of the virus. Through our collected Twitter dataset, we validate the existence of the spillover effects. Building on this finding, we propose extensions to three cascade prediction methods based on Graph Neural Networks (GNNs). Experiments conducted on our dataset demonstrated that the use of the identified spillover effects significantly improves the state-of-the-art GNN methods in predicting the popularity of not only preventive measure messages, but also other COVID-19 messages. |
first_indexed | 2024-03-09T22:02:00Z |
format | Article |
id | doaj.art-d4aa6940b5f34eb2b680fc30b4a80170 |
institution | Directory Open Access Journal |
issn | 1099-4300 |
language | English |
last_indexed | 2024-03-09T22:02:00Z |
publishDate | 2022-01-01 |
publisher | MDPI AG |
record_format | Article |
series | Entropy |
spelling | doaj.art-d4aa6940b5f34eb2b680fc30b4a801702023-11-23T19:47:56ZengMDPI AGEntropy1099-43002022-01-0124222210.3390/e24020222Exploring Spillover Effects for COVID-19 Cascade PredictionNinghan Chen0Xihui Chen1Zhiqiang Zhong2Jun Pang3Faculty of Sciences, Technology and Medicine, University of Luxembourg, L-4364 Esch-sur-Alzette, LuxembourgInterdisciplinary Centre for Security, Reliability and Trust, University of Luxembourg, L-4364 Esch-sur-Alzette, LuxembourgFaculty of Sciences, Technology and Medicine, University of Luxembourg, L-4364 Esch-sur-Alzette, LuxembourgFaculty of Sciences, Technology and Medicine, University of Luxembourg, L-4364 Esch-sur-Alzette, LuxembourgAn information outbreak occurs on social media along with the COVID-19 pandemic and leads to an <i>infodemic</i>. Predicting the popularity of online content, known as <i>cascade prediction</i>, allows for not only catching in advance information that deserves attention, but also identifying false information that will widely spread and require quick response to mitigate its negative impact. Among the various information diffusion patterns leveraged in previous works, the <i>spillover effect</i> of the information exposed to users on their decisions to participate in diffusing certain information has not been studied. In this paper, we focus on the diffusion of information related to COVID-19 preventive measures due to its special role in consolidating public efforts to slow down the spread of the virus. Through our collected Twitter dataset, we validate the existence of the spillover effects. Building on this finding, we propose extensions to three cascade prediction methods based on Graph Neural Networks (GNNs). Experiments conducted on our dataset demonstrated that the use of the identified spillover effects significantly improves the state-of-the-art GNN methods in predicting the popularity of not only preventive measure messages, but also other COVID-19 messages.https://www.mdpi.com/1099-4300/24/2/222cascade predictioninformation diffusionCOVID-19graph neural networksspillover effectsTwitter |
spellingShingle | Ninghan Chen Xihui Chen Zhiqiang Zhong Jun Pang Exploring Spillover Effects for COVID-19 Cascade Prediction Entropy cascade prediction information diffusion COVID-19 graph neural networks spillover effects |
title | Exploring Spillover Effects for COVID-19 Cascade Prediction |
title_full | Exploring Spillover Effects for COVID-19 Cascade Prediction |
title_fullStr | Exploring Spillover Effects for COVID-19 Cascade Prediction |
title_full_unstemmed | Exploring Spillover Effects for COVID-19 Cascade Prediction |
title_short | Exploring Spillover Effects for COVID-19 Cascade Prediction |
title_sort | exploring spillover effects for covid 19 cascade prediction |
topic | cascade prediction information diffusion COVID-19 graph neural networks spillover effects |
url | https://www.mdpi.com/1099-4300/24/2/222 |
work_keys_str_mv | AT ninghanchen exploringspillovereffectsforcovid19cascadeprediction AT xihuichen exploringspillovereffectsforcovid19cascadeprediction AT zhiqiangzhong exploringspillovereffectsforcovid19cascadeprediction AT junpang exploringspillovereffectsforcovid19cascadeprediction |