Causal Modeling of Twitter Activity during COVID-19

  1. Oguzhan Gencoglu
  2. Mathias Gruber

Reviewed by

Read the full article

Listed in

Log in to save this article

Abstract

Understanding the characteristics of public attention and sentiment is an essential prerequisite for appropriate crisis management during adverse health events. This is even more crucial during a pandemic such as COVID-19, as primary responsibility of risk management is not centralized to a single institution, but distributed across society. While numerous studies utilize Twitter data in descriptive or predictive context during COVID-19 pandemic, causal modeling of public attention has not been investigated. In this study, we propose a causal inference approach to discover and quantify causal relationships between pandemic characteristics (e.g., number of infections and deaths) and Twitter activity as well as public sentiment. Our results show that the proposed method can successfully capture the epidemiological domain knowledge and identify variables that affect public attention and sentiment. We believe our work contributes to the field of infodemiology by distinguishing events that correlate with public attention from events that cause public attention.

Article activity feed

  1. Version published to 10.3390/computation8040085
  2. ScreenIT

    SciScore for 10.1101/2020.05.16.20103903: (What is this?)

    Please note, not all rigor criteria are appropriate for all manuscripts.

    Table 1: Rigor

    NIH rigor criteria are not applicable to paper type.

    Table 2: Resources

    No key resources detected.

    Results from OddPub: Thank you for sharing your code and data.

    Results from LimitationRecognizer: We detected the following sentences addressing limitations in the study:
    We would like to emphasize that we acknowledge these and other relevant limitations of our study. Our study has further limitations regarding the simplifications on our problem formulation and data. For instance, we do not attempt to model temporal causal relationships in this study, e.g., high deaths numbers having an impact on the public sentiment possibly for several following days. We have not taken into account remarks by famous politicians, public figures, or celebrities which may indeed impact social media discussions. We have not incorporated “retweets” or “likes” into our models either. Future work includes investigating the effect of dynamics of the pandemic on the spreading mechanisms of information, including relevant health topics in Twitter and other social media. As social media can be exploited for deliberately creating panic and confusion [89], causal inference on patterns of misinformation and disinformation propagation in Twitter will be studied as well. Finally, country-specific models with more granular statistics of the country will be investigated.

    Results from TrialIdentifier: No clinical trial numbers were referenced.

    Results from Barzooka: We did not find any issues relating to the usage of bar graphs.

    Results from JetFighter: We did not find any issues relating to colormaps.

    Results from rtransparent:
    • Thank you for including a conflict of interest statement. Authors are encouraged to include this statement when submitting to a journal.
    • Thank you for including a funding statement. Authors are encouraged to include this statement when submitting to a journal.
    • No protocol registration statement was detected.

    About SciScore

    SciScore is an automated tool that is designed to assist expert reviewers by finding and presenting formulaic information scattered throughout a paper in a standard, easy to digest format. SciScore checks for the presence and correctness of RRIDs (research resource identifiers), and for rigor criteria such as sex and investigator blinding. For details on the theoretical underpinning of rigor criteria and the tools shown here, including references cited, please follow this link.

  3. Version published to 10.1101/2020.05.16.20103903v1 on medRxiv