COVID-19 case prediction using emotion trends via Twitter emoji analysis: A case study in Japan

Abstract

IntroductionThe worldwide COVID-19 pandemic, which began in December 2019 and has lasted for almost 3 years now, has undergone many changes and has changed public perceptions and attitudes. Various systems for predicting the progression of the pandemic have been developed to help assess the risk of COVID-19 spreading. In a case study in Japan, we attempt to determine whether the trend of emotions toward COVID-19 expressed on social media, specifically Twitter, can be used to enhance COVID-19 case prediction system performance.MethodsWe use emoji as a proxy to shallowly capture the trend in emotion expression on Twitter. Two aspects of emoji are studied: the surface trend in emoji usage by using the tweet count and the structural interaction of emoji by using an anomalous score.ResultsOur experimental results show that utilizing emoji improved system performance in the majority of evaluations.

Analysis of green deal communication on twitter: environmental and political perspective

“…Twitter has become a legitimate research platform providing a large quantity of real-time data. These data provide insight into people's opinions on various issues (Gaytan Camarillo et al, 2021;Hussain et al, 2021;Prieto Santamaría et al, 2022), the possibility to analyze tweet sentiment (Ballestar et al, 2020;Vargas et al, 2021;Hassan et al, 2022;Park et al, 2022), and the ability to identify trends in communication (Tran and Matsui, 2023). According to published statistics, the Twitter social platform had 368 million active users per month worldwide, as of December 2022 (X/Twitter: number of users worldwide 2024, 2024).…”

“…As mentioned above, society faces a significant challenge in climate change. In the last 50 years, the global conversation on climate change, global warming, and sustainability has also grown (Lipschultz, 2017;Sabherwal and Kácha, 2021), which evokes certain emotions, feelings, and reactions in individuals (Hayes et al, 2018;Stanley et al, 2021;Pihkala, 2022;Tran and Matsui, 2023). Likewise, issues related to the Green Deal and whether it will fulfil its aim of sustainable transformation are of concern to all stakeholders affected by the deal (Ossewaarde and Ossewaarde-Lowtoo, 2020;Eckert and Kovalevska, 2021;Fleming and Mauger, 2021;Ringel et al, 2021;Samper et al, 2021;Schuelke-Leech, 2021;Hereu-Morales et al, 2023).…”

Bibliometric analysis of literature on social media trends during the COVID-19 pandemic

“…Previous research has often neglected the role of hashtags as a social media functionality (Weller, 2016). Nonetheless, the evolution of social media platforms has underscored the significance of studies on trending topics, a trend that gained traction during the COVID-19 pandemic (Ahmed et al, 2020b(Ahmed et al, , 2021Boon-Itt and Skunkan, 2020;Han et al, 2020;Tran and Matsui, 2023;Zhao et al, 2020). These topics provide a digital space for users to share perspectives on shared interests.…”

“…Previous research has examined trending topic taxonomy (Cahyani and Putra, 2021), detection (Ahmed et al, 2020a(Ahmed et al, , 2021, predictive analysis (Irshad et al, 2023;Tran and Matsui, 2023), sentiment analysis and topic modelling (Wang et al, 2023;Khan et al, 2023). Nonetheless, these studies may not be exhaustive.…”

“…Current publications predominantly focus on COVID-19-related issues, particularly in 2021. Researchers are concerned with the generation and dissemination of misinformation during the pandemic, with a keen focus on the communication gaps between the government and the public (Tran and Matsui, 2023;Wang et al, 2019). A recent study in China revealed that during the pandemic, Chinese citizens' adoption of e-government information services on social media was primarily influenced by information quality, credibility and perceived ease of use (Mensah et al, 2022).…”