Public wellbeing analytics framework using social media chatter data.

Area of Science:

• Social Sciences
• Computational Social Science
• Public Health

Background:

• Public wellbeing is a key governmental priority.
• Analyzing public sentiment and wellbeing is complex.
• Existing methods lack continuous, large-scale analysis capabilities.

Purpose of the Study:

• To develop an end-to-end framework for public wellbeing analytics.
• To predict public wellbeing status using social media content.
• To provide spatiotemporal insights for decision-making.

Main Methods:

• A novel distant supervision approach for generating wellbeing-labeled datasets.
• A wellbeing prediction model utilizing BERT contextualized sentence embeddings.
• Spatiotemporal analytics for visualizing wellbeing trends.

Main Results:

• The proposed framework effectively predicts public wellbeing status.
• The distant supervision approach successfully generates labeled datasets.
• Spatiotemporal analytics provide actionable insights for policymakers.

Conclusions:

• The developed framework offers a robust method for continuous public wellbeing monitoring.
• This approach can significantly aid governments in evaluating policy impacts.
• Social media analysis provides valuable data for understanding public wellbeing.