Deep Learning-based Infodemic Models To Assess Impact of Infodemics on COVID-19 Emergency Responses

Table: 6
Experimentation location: Home
Regulated Research (Form 1c): No
Project continuation (Form 7): No

Display board image not available


The goal of the project is to design Deep Learning (DL) based models to identify the infodemics and assess its impact on COVID-19 remedial measures. Infodemic is a blend of "information" and "epidemic" that typically refers to a rapid and far-reaching spread of both accurate and inaccurate information about something, such as a disease. Modeling methods, such as SEIR model, used to assess or predict COVID-19 spread are not effective for infodemic because infodemic spreads at a large exponent than a pandemic. DL models such as transformer-based approaches proved to be more effective in identifying high-impact infodemics. When the approaches have been used against WHO’s social media data, the infodemic topics involving vaccines or treatments seem to have adverse impacts than topics covering causes of the virus.


[1] Heng, Kevin, and Christian L. Althaus. “The Approximately Universal Shapes of Epidemic Curves in the Susceptible-Exposed-Infectious-Recovered (SEIR) Model.” Nature News, Nature Publishing Group, 9 Nov. 2020, 

[2] “Infodemic Management of WHO Information NetWork for Epidemics.” World Health Organization, World Health Organization, 

[3] Li HOY, Bailey A, Huynh D, Chan J (2020) YouTube as a source of information on COVID-19: A pandemic of misinformation? BMJ Glob. Heal. 5(5):2604.

[4] Islam MS, Sarkar T, Khan SH, Mostofa Kamal AH, Hasan SMM, Kabir A, Yeasmin D, et al. (2020) COVID-19–Related Infodemic and Its Impact on Public Health: A Global Social Media Analysis. Am. J. Trop. Med. Hyg.:tpmd200812.


Additional Project Information

Project website: -- No project website --
Presentation files:
Research paper:
Additional Resources: -- No resources provided --
Project files:
Project files

Research Plan:



Effective mitigation of the Coronavirus disease (COVID-19) or any other global pandemic relies on the people’s trust and adherence to the recommendations of established scientific bodies. The misinformation transmitted through infodemics is detrimental to individual’s physical and mental health, elevates stigmatization and hate speech, threatens precious health gains, leads to the poor observation of public health measures, and even costs lives [2]. A recent study shows that more than 35% of the most viewed COVID-19 related videos contain misinformation [3]. Among those misinformation videos, one myth – that highly concentrated alcohol consumption could disinfect the coronavirus – infiltrated the public’s belief and claimed over 800 lives [4]. Misinformation and distrust can be a particularly dangerous combination that causes people to reject health interventions such as vaccines, disregard health guidance, or try out unproven and dangerous therapies like ingesting methanol to prevent COVID-19.  

Modeling methods, such as SEIR model, used to assess or predict the COVID-19 spread are not effective because infodemic spreads exponentially in the digital world. Factors such as large growth exponent and speed of infodemic spread require advanced Deep Learning approaches.

Research Questions:

  1. How effective are traditional pandemic modeling approaches when applied to infodemic assessment?
  2. What are the alternative approaches for infodemic modeling and which ones are more effective globally?
  3. How do we measure the impact of infodemic on the COVID-19 emergency responses?






Questions and Answers

1. What was the major objective of your project and what was your plan to achieve it? 

The major objective of the project is to find effective modeling approaches for infodemic spread and prioritize the mitigation strategies.

       a. Was that goal the result of any specific situation, experience, or problem you encountered?  

Infodemic is impacting the emergency responses in adverse ways and somewhat responsible for the spike in COVID-19 cases and deaths.

       b. Were you trying to solve a problem, answer a question, or test a hypothesis?

Solve the problem by identifying the effective modeling approaches of infodemics.

2. What were the major tasks you had to perform in order to complete your project?

i) Identify traditional modeling approaches of COVID-19 spread

ii) Test if the approaches are effective in modeling infodemic spread

iii) Research to find if alternative approaches are available to model the infodemic spread

iv) Rank the effectiveness of the approaches

       a. For teams, describe what each member worked on.

I had worked on the project alone.

3. What is new or novel about your project?

Using Deep Learning to model infodemic spread.

       a. Is there some aspect of your project's objective, or how you achieved it that you haven't done before?

Everything I am doing in the project is new and had to start basic research to identify if infodemic impact is a significant problem in emergency responses.

       b. Is your project's objective, or the way you implemented it, different from anything you have seen?

Both, the objective and implementation, are unique.

       c. If you believe your work to be unique in some way, what research have you done to confirm that it is?

I had reviewed WHO sites and other research sites to understand if there any models exist for infodemic spread.

4. What was the most challenging part of completing your project?

All topics of COVID-19 spread and infodemic impacts are new to me and I had to do a lot of reading before starting the project.

      a. What problems did you encounter, and how did you overcome them?

The biggest problem is to identify datasets to evaluate the models developed. Also, there was a lot of mathematics like Linear Algebra that I had to learn in very little time.

      b. What did you learn from overcoming these problems?

I had learned about epidemiological modeling, Linear Algebra for building Deep Learning, Transformers for going through large news datasets, and Flourish software to prepare good visualizations.

5. If you were going to do this project again, are there any things you would you do differently the next time?

I would limit the scope of the project to the identification of the models for infodemic spread. I could have tried different models with different parameters to identify impacts with a higher level of accuracy.

6. Did working on this project give you any ideas for other projects? 

It had generated few ideas such as co-relation of infodemic areas and an integrated approach to mitigate all of them at same time.

7. How did COVID-19 affect the completion of your project?

COVID-19 didn't affect the completion of the project, though I would have loved the idea of presenting it to experts and get their inputs to improve the project and outcomes.