Mining internet media for monitoring changes of public emotions about infectious diseases

Abstract

The Internet encompasses websites, email, social media, and Internet-based television. Given the widespread use of networked computers and mobile devices, it has become possible to monitor the behavior of Internet users by examining their access logs and queries. Based on large-scale web and text mining of Internet media articles and associated user comments, we propose a framework to rapidly monitor how the emotion of the public changes over time and apply the framework to a real case of an infectious disease. The proposed methodology will be helpful for performing cost-effective and time-efficient public health monitoring that otherwise would take orders-of-magnitude more time and resources if traditional epidemiology techniques were used.

Amplifying Panic and Facilitating Prevention: Multifaceted Effects of Traditional and Social Media Use During the 2015 MERS Crisis in South Korea

“…Often, information intertwined with emotional markers travels around social media, and emotionally charged messages are more likely than purely informational posts to be shared and diffused (Pfeffer, Zorbach, & Carley, 2014;Stieglitz & Dang-Xuan, 2013). S. Choi, Lee, Pack, Chang, and Yoon (2016) mined Internet media reports about MERS in 2016 and examined their effects on public emotion expressed online, which they captured using a sentiment analysis. They mined all MERS-related news articles from 153 media companies, including the comments about each one.…”

Large-scale machine learning of media outlets for understanding public reactions to nation-wide viral infection outbreaks

“…In this paper, by significantly extending our prior work [41], we analyzed the interaction among disease, media and public. Unlike precedent research mostly dealing with non-anonymous data (such as Twitter or Facebook), our methods using comments guarantee the anonymity of the public.…”

“…Towers et al [40] analyzed the potential influence between Ebolarelated news and Ebola-related searches or tweets using a mathematical model of contagion. In our prior work [41], we performed proof-of-concept experiments to test the effectiveness of social media-based analysis of public reactions to widespread infectious diseases such as MERS.…”

“…This attribute of data helps reflect the public emotion as it is. Compared with our prior work [41], this paper proposes more advanced methodologies that can process a larger-scale dataset with more delicate detection of sig-nals in texts, along with a more extensive set of experiments that can verify the effectiveness of our approach for real-world media outlet datasets.…”

Characterizing Online Media on COVID-19 during the Early Months of the Pandemic

“…These studies demonstrate that news articles, web blogs, social media, and discussion forums are effective indicators of influenza activity including in the H5N1 (2004), H1N1 (2009), and H7N9 (2013) pandemics. Text and structural data mining of these media has been applied in monitoring disease trends and behavioral risk factors (Paul and Dredze 2011), evaluating public responses to health crises (Choi et al 2016;Chew and Eysenbach 2010), and identifying online communities for targeted public health communication (Corley et al 2010).…”