# Government Predictive Accuracy Boosted by AI-Powered Social Media Intelligence

> Leading Government Department · Public Sector · QuantSpark Labs

How QuantSpark improved the performance of an existing predictive model that wasn't delivering the accuracy needed for effective decision-making for a national security customer.

## What was the problem?

The department’s existing predictive model was not accurate enough to provide useful forecasts, nor flexible enough to enable vital scenario planning to inform decision-making. This meant that the department was frequently surprised by both real-world events and the results of their decisions, incurring costs significant enough to be a major concern at a national level.

When predictive models underperform, the usual approach is to refine the existing data inputs or adjust the model's parameters. However, we proposed a different hypothesis – what if the model was missing a critical data source entirely? Specifically, we suggested that social media conversations might contain valuable signals that could enhance the model’s predictive power.

## What did QuantSpark do?

To test this hypothesis, we developed a methodology to systematically analyse social media discussions across various dimensions, based on the following activities:

*   **Intelligence-Driven Research**: We began with comprehensive open-source intelligence (OSINT) research to identify the characteristics of relevant content. This foundational step helped us understand what to look for in the vast ocean of social media data.
*   **Strategic Data Collection**: Working with a specialised third-party provider, we sourced millions of social media posts in a manner compliant with GDPR, using our OSINT findings to focus on the most relevant content for the project's objectives.
*   **Advanced Content Categorisation**: We employed a large language model (LLM) to systematically categorise the collected content based on relevance, key topics for our use case, and geographic associations, creating a structured dataset from unstructured conversations.

With our dataset in place, we conducted rigorous statistical analysis through a series of hypothesis tests. These tests were designed to evaluate whether the social media signals we had identified could actually improve predictive power for the outcomes the government department was interested in.

## What changed?

The results were compelling: we discovered statistically significant relationships between our aggregated social media dataset and the real-world outcomes the department needed to forecast. There were clear correlations both when analysing changes over time and differences between geographies. This confirmed our initial hypothesis that social conversations contain valuable predictive information that had been missing from their model.

We also developed a roadmap detailing how such an approach could be scaled, automated and extended. One key learning was that while AI processing costs are falling, realistically, with a limited budget, it remains necessary to initially filter the content using less computationally intensive techniques, so as not to run an excessive number of queries for each relevant post identified. This is why the initial OSINT research was so crucial to our process in this project.

By systematically collecting, categorising and analysing these social media conversations, we've laid the groundwork for incorporating these insights into the department's predictive framework, in a way that would enable much-improved forecasting and scenario planning capabilities.

---

Canonical page: https://quantspark.ai/case-studies/government-predictive-accuracy-boosted-by-ai-powered-social-media-intelligence
More about QuantSpark: https://quantspark.ai/llms.txt