Select Page

ESG at Semantic Web Company

May 8, 2023

Angela DaSilva

Angela DaSilva

Content Strategist


All Blog posts

In the next coming years, Environmental Social Governance (ESG) initiatives and regulations will keep organizations quite busy with ensuring they are compliant. The EU, for example, has issued a mandate where by 2024, a predefined set of large companies have to begin reporting on their sustainability efforts – the mandate will trickle down to smaller companies in the years soon after. 

Though the mandate does not directly influence us at Semantic Web Company yet, we are still committed to acting on ESG initiatives early. Internally, we have begun implementing policies that reflect sustainabilty from a structrual and company culture standpoint. For external purposes, we have been developing products that can help other organizations remain compliant with ESG.

This blog gives an overview on all our recent activities related to the topic. 

ESG and Sustainability AI Solutions

Investors and corporate clients use Semantic Web Company’s ESG solutions to gain deep insights into the ESG performance of companies in the context of value chains, portfolios or industry comparisons. Compliance checks along predefined frameworks and individually configurable ESG criteria are supported as well as smart recommendations regarding possible opportunities.

Check out our customers, solutions, and use cases here.

ESG Knowledge Hub

 ​​With our newest demo application, you can ask a graph-infused LLM environmental-related questions and it will provide answers, follow-ups, recommended articles, and summaries.

This application combines symbolic AI (knowledge graphs) and generative AI (LLM) for better domain fidelity and fewer hallucinations. It uses natural language processing and semantic search to ensure that documents are found based on the user’s intent of the query, as well as generates new content and summaries about this topic while in dialogue with the chatbot. 


PoolParty Meets ChatGPT

First released by a company called OpenAI in November, ChatGPT is a large language model that has been celebrated for its ability to generate texts based on questions asked by the user. 

While ChatGPT has had a monumental impact on the world of chat bots, it does have its limitations. Aside from having virtually no explainability (in other words, the sources it derives its answers from are not transparent), it often provides inaccurate or abbreviated summaries to questions that could otherwise be filled with information.

In response to this, the PoolParty Team created PoolParty Meets ChatGPT, which adds an additional layer to ChatGPT that not provides more comprehensive answers and enrichens the answers with sources from the knowledge graph.

This image shows how the answers from ChatGPT compare to answers enriched with a knowledge graph.

See the difference in answer quality? You can ask the model your own ESG-specific questions for free.

ESG Knowledge Model

Both these applications rely on the ESG Core Knowledge Model, a knowledge model built by SWC specifically for the ESG domain.

The knowledge model has been created and refined based on extensive research conducted over the last half year. The research was first put into a taxonomy in PoolParty and then embedded in a knowledge graph. 

The knowledge model can be used as a reference point for reporting, the foundations for an ESG Knowledge Hub, and so on. In our own organization, we are using it as a Knowledge Hub to educate employees about the topic and measure our actitives against ESG standards.

Stay tuned for more very soon!

ESG Risk Management

Below the surface, ESG presents a lot of corporate risks: compliance risk, investment risk, supply chain risk, and reputation risk. The underlying problem associated with these risks is that organizations lack clarity on standards and are fed data from too many sources.

A dedicated ESG Knowledge Model can help organizations get a better holistic picture of the data and actively manage their risks. Read more about the PoolParty Knowledge Model and specific use cases in this leaflet.

Webinar: ESG Strategies with Semantic AI

In this webinar, we introduced the ESG topic and showed that the use of a comprehensive ESG knowledge model can support the implementation of ESG strategies in a multitude of ways. 

Led by Semantic Web Company CEO Andreas Blumauer, this webinar touched on some of the following key topics:

  • Demos of the ESG Knowledge Hub and PoolParty Meets ChatGPT
  • How to integrate a knowledge model across different interests
  • The ESG hierarchical target systems (e.g. SDGs, EU taxonomy, etc.)
  • Multi-layered regulatory conditions in complex, dynamic knowledge domains
  • Real-life PoolParty case studies 

ESG case studies with PoolParty.

Since it is such a complex topic, many organizations see ESG implementation as a daunting task. But it doesn’t have to be! 

Don’t believe us? We’ve put together 6 videos of presentations from our recent PoolParty Summit 2023 that reflect the different dimensions of ESG (environmental, social, governance). Check out some sample case studies to see how our customers and partners have used PoolParty together with ESG. 

How Semantic AI can ease your way to sustainable business.

We’ve also compiled information related to ESG and Semantic AI into a leaflet. Download it for free to get the common use cases, some PoolParty-specific success stories, and more.

And many more to come!
We are working very intensively with ESG, and we want to continue to make a difference. Check back here for any updates related to our ESG activities and products. 

Want to learn more about our ESG projects? Reach out to us!

You may also like these blogs …

The age of hyper-personalization has dawned

The age of hyper-personalization has dawned

Being able to precisely meet the individual information needs of their customers, including with micro-content, will have to become more of a core competency for specialist publishers. In this interview, Andreas Blumauer explains the important role that knowledge models play in this and why LLMs cannot do this alone.

read more