​

Introduction

This notebook demonstrates how advanced narrative mining reveals evolving market stories across multiple document types. We will track the “AI Bubble Concerns” narrative as it emerges and evolves across news, earnings calls, and regulatory filings – highlighting the difference between public discourse and corporate communications. The bigdata-research-tools package provides a specialised class, NarrativeMiner, for narrative mining. We can specify the document_type parameter to be DocumentType.NEWS, DocumentType.TRANSCRIPTS, DocumentType.FILINGS to be able to:

• Analyze web-based news content
• Examine earnings call and event transcripts
• Explore SEC Filings from EDGAR

Each Narrative Miner instance follows the same workflow:

• Define narrative labels which encompass a theme
• Retrieve content using Bigdata’s search capabilities
• Label content with LLMs to identify narrative matches
• Analyze the results to reveal patterns and insights

Ready to get started? Let’s dive in!

​

Conclusion

The Narrative Miner stands as a powerful analytical framework that transforms unstructured textual data into actionable intelligence by identifying and tracking thematic narratives across diverse sources.

By layering document types—comparing what’s being said in news media against earnings transcripts and regulatory filings—users gain a multi-dimensional view of how narratives evolve and propagate. These patterns reveal not just what is being discussed, but how different stakeholders are positioning themselves relative to emerging trends.

The time-series visualization of narrative intensity often surfaces leading indicators of market sentiment shifts provides valuable foresight for investors seeking to anticipate market movements before they manifest in price action.

The NarrativeMiner’s flexibility allows it to be deployed across countless domains—from tracking sustainability commitments in corporate governance to identifying early signs of supply chain disruptions or monitoring the public reception of product innovations. Its integration with BigData’s search capabilities and modern LLM technology makes it particularly effective at processing large volumes of documents efficiently. As you incorporate narrative mining into your research workflow, consider experimenting with different narrative formulations, document sources, and time horizons to discover the combination that yields the most valuable signals for your specific analytical needs.

Enjoy exploring and extending your narrative analysis!