Primer partnered with Vibrant Data Labs and the Cisco Foundation to create the first-ever map of the climate change funding landscape.

Using Natural Language Processing, we mapped the state of private funding across climate change.

Here's why that matters.

Climate change as a social issue

Primer partnered with Eric Berlow of Vibrant Data Labs to produce the first-ever climate change funding map based on the analysis of thousands of company tags and labels. This unique perspective comes bottom-up from how the private and social sector organizations on the ground describe what they do — not by what is most spoken about in the news or social media.

Primer’s natural language processing (NLP) technology analyzed data on over 12,000 companies and nonprofits funded in the last five years. Using organizations’ descriptions provided by Crunchbase and Candid, we generated one of the first-ever, data-driven conceptual hierarchy of topics to better understand the shape of our current response, and its potential gaps.

How NLP reads for meaning.

What's so unique about a climate change map? Using NLP techniques, we can do analysis the same way as a human would. Historically, AI was simply matching words and counting words. But now, it's actually reading for meaning.

The Coronavirus pandemic was like the trailer to the climate change movie.
-Eric Berlow

When machines read like humans

With natural language processing, machines read and write to the same ability as a human. NLP isn't just matching keywords, but understanding the full context of what a word means - with massive implications for our world.

We developed a prototype pipeline to help address this broad use case as part of our work with Vibrant Data Labs. The pipeline is designed to ingest an arbitrary set of documents, produce a hierarchical visualization of the contents, and finally make the corpus searchable by tagging each document with both specific and broad keywords.

In this post, we’ll present the pipeline’s methodological design. As we’ll see, it opens up new ways of tackling text analysis tasks.

We used NLP to analyze the work of over 12,000 companies to better understand where private and public organizations were focusing their efforts.
Before NLP, creating this type of map was not possible.
With this map, funders in climate change - for the first time - have a searchable database of who is working on what for climate change.

Search using hierarchical text

Learn more about the value of hierarchical text clustering, and how it opens up new ways of tackling text analysis tasks.

Build your own models from scratch or use Primer models off-the-shelf. Anyone in your organization can build and train models using Primer Platform — no coding or technical skills required.

Pre-Trained Models

Primer's API can integrate data with your unique applications and diverse workflows. The API allows you to convert unstructured text in meaningful ways such as:

More about Primer

Primer lets organizations quickly explore and utilize the world’s exponentially growing sources of text-based information. Our best-in-class machine intelligence solutions help you answer complex questions in real time with human-level precision.