Dow Jones Factiva
Dow Jones Factiva turns the world's news into business intelligence — but making sense of the qualifying articles still fell to analysts reading them by hand. With Lead Semantics (LangOptima's partner), we built a knowledge graph that reads the news automatically, so the facts are queryable without a person reading every article.
The challenge
Factiva already narrows the news with powerful codes — subject, industry, region, company. But understanding the qualifying articles still fell to human analysts, and that reading is the bottleneck. Dow Jones watched customers try to solve it alone and struggle.
“We have a lot of customers who are trying to do this on their own. And they are really struggling with working with unstructured text, how news is reported, and how it affects the business world. That's still a challenge today. And we're not familiar with anyone that has the perfect, out of the box solution.”
— Ezra Duong-Van, Dow Jones
What we did
We focused the first pilot on ESG — a domain of growing importance that traditional news monitoring handles poorly. Lead Semantics' TextDistil, an NLP and semantic-graph platform, was trained to use Factiva's codes and ingest Factiva search results, producing a knowledge graph of ESG and investment facts from the articles. That graph powers two things: instantly verifiable (augmented) semantic search, and an enterprise knowledge graph populated with facts from the news for ongoing analytics.
“One of the biggest appeals of Lead Semantics is that they enable customers to take a large volume of articles and make sense of them. They offer a very good solution today that does this.”
— Ezra Duong-Van, Dow Jones
The result
The integration extended Factiva with knowledge-graph analytics and search, letting users:
- Monitor and assess companies' ESG performance in near real-time.
- Identify risks and opportunities tied to ESG events.
- Understand how news events correlate with ESG impact.
- Analyze industry trends and benchmarks in an ESG context.
“It's not necessarily just the performance gains, but it's something that's repeatable… rather than reading 50 articles, we can cover 500 articles or 5000 articles or so on. So it's being able to expand your ability to not only find a needle in a much bigger haystack, but it's also to programmatically keep that running on a regular basis at a much lower cost.”
— Ezra Duong-Van, Dow Jones
“Anything that's captured in the news is a good candidate… the use cases are all over the map.”
— Ezra Duong-Van, Dow Jones
Written by Joaquin Melara (Lead Semantics, partner of LangOptima), with commentary from Ezra Duong-Van (Dow Jones). Watch the full webinar →