Exploring happiness factors with explainable ensemble learning in a global pandemic
2025

Exploring Happiness Factors During a Global Pandemic

Sample size: 156 publication 20 minutes Evidence: high

Author Information

Author(s): Hamja Md Amir, Hasan Mahmudul, Rashid Md Abdur, Shourov Md Tanvir Hasan

Primary Institution: Hajee Mohammad Danesh Science and Technology University, Dinajpur, Bangladesh

Hypothesis

How do various factors influence happiness scores during and after the COVID-19 pandemic?

Conclusion

The study found that GDP per capita, social support, and healthy life expectancy are key indicators of happiness, with social support becoming the most important during the pandemic.

Supporting Evidence

  • The study utilized an open dataset from the World Happiness Report, covering 156 countries from 2018 to 2023.
  • Blending RGMLL model demonstrated the highest predictive accuracy with R2 of 85%, MSE of 0.15, and RMSE of 0.38.
  • During the pandemic, social support emerged as the most important indicator of happiness.

Takeaway

This study looks at what makes people happy during tough times like a pandemic, showing that having friends and support is super important.

Methodology

The study used machine learning and deep learning models to predict happiness scores based on data from the World Happiness Report covering 156 countries from 2018 to 2023.

Limitations

The model's performance can be compromised by including underperforming models in the ensemble.

Participant Demographics

Data from 156 countries was analyzed, covering various demographics.

Digital Object Identifier (DOI)

10.1371/journal.pone.0313276

Want to read the original?

Access the complete publication on the publisher's website

View Original Publication