SIG SM Digest June 2021 - Publications
Measuring and profiling the topical influence and sentiment contagion of public event stakeholders
Author(s): Lu An, Wenjing Zhou, Menghua Ou, Gang Li, Chuanming Yu and Xiaofen Wang
Citation: An, L., Zhou, W., Ou, M., Li, G., Yu, C., & Wang, X. (2021). Measuring and profiling the topical influence and sentiment contagion of public event stakeholders. International Journal of Information Management, 58, 102327. doi: https://doi.org/10.1016/j.ijinfomgt.2021.102327
Abstract: When public events occur, users often generate a huge number of microblog entries and their online interactions with one another. Forwarding and commenting on posts contribute to the huge networks of topic and sentiment communication. This study constructs the topic and sentiment propagation maps of microblogging in the context of public events to visually explore the patterns of topic and sentiment propagation among stakeholders across different phases. To quantify the influence of topic and sentiment propagation, four indicators of “topic out-degree,” “topic variation degree,” “sentiment out-degree,” and “sentiment deviation degree” are proposed. We chose the child abuse case in the Beijing Red-Yellow-Blue (RYB) Kindergarten for our study. The positions of various stakeholders in the propagation paths and the relationship among stakeholders were revealed. Results indicate that the government and mainstream media have the greatest influence in terms of topic and sentiment propagation. Moreover, topic propagation was the most influential in the recession phase and the same can be said with sentiment propagation in the spreading phase. The findings can help the emergency management departments gain a better understanding of the propagation patterns of topics and emotions and the role of stakeholders in such phenomena to improve their emergency response ability.
Identifying and Analyzing Health-Related Themes in Disinformation Shared by Conservative and Liberal Russian Trolls on Twitter
Dr. Karami published a paper at International Journal of Environmental Research and Public Health on developing a framework to identify and analyze health topics shared by Russian trolls between 2012 and 2018. We found that there were not just a few health issues (e.g., vaccines), Russian Trolls polarized Americans on a wide range of health topics.
Citation: Karami, A.; Lundy, M.; Webb, F.; Turner-McGrievy, G.; McKeever, B.W.; McKeever, R. Identifying and Analyzing Health-Related Themes in Disinformation Shared by Conservative and Liberal Russian Trolls on Twitter. International Journal of Environmental Research and Public Health 2021, 18, 2159. https://doi.org/10.3390/ijerph18042159
Abstract: To combat health disinformation shared online, there is a need to identify and characterize the prevalence of topics shared by trolls managed by individuals to promote discord. The current literature is limited to a few health topics and dominated by vaccination. The goal of this study is to identify and analyze the breadth of health topics discussed by left (liberal) and right (conservative) Russian trolls on Twitter. We introduce an automated framework based on mixed methods including both computational and qualitative techniques. Results suggest that Russian trolls discussed 48 health-related topics, ranging from diet to abortion. Out of the 48 topics, there was a significant difference (p-value ≤ 0.004) between left and right trolls based on 17 topics. Hillary Clinton's health during the 2016 election was the most popular topic for right trolls, who discussed this topic significantly more than left trolls. Mental health was the most popular topic for left trolls, who discussed this topic significantly more than right trolls. This study shows that health disinformation is a global public health threat on social media for a considerable number of health topics. This study can be beneficial for researchers who are interested in political disinformation and health monitoring, communication, and promotion on social media by showing health information shared by Russian trolls.
An iSchool approach to data science: Human-centered, socially responsible, and context-driven
Dr. Hagen co-authored a paper published at Journal of the Association for Information Science and Technology to declare the unique approach of iSchool's Data Science education that includes three distinct components: human-centeredness, socially responsible, and rooted in context.
Citation: Shah, C., Anderson, T., Hagen, L., & Zhang, Y. (2021). An iSchool approach to data science: Human-centered, socially responsible, and context-driven. Journal of the Association for Information Science and Technology. https://doi.org/10.1002/asi.24444
Abstract: The Information Schools, also referred to as iSchools, have a unique approach to data science with three distinct components: human-centeredness, socially responsible, and rooted in context. In this position paper, we highlight and expand on these components and show how they are integrated in various research and educational activities related to data science that are being carried out at iSchools. We argue that the iSchool way of doing data science is not only highly relevant to the current times, but also crucial in solving problems of tomorrow. Specifically, we accentuate the issues of developing insights and solutions that are not only data-driven, but also incorporate human values, including transparency, privacy, ethics, fairness, and equity. This approach to data science has meaningful implications on how we educate the students and train the next
generation of scholars and policymakers. Here, we provide some of those design decisions, rooted in evidence-based research, along with our perspective on how data science is currently situated and how it should be advanced in iSchools.