Do you remember the
Pandora Papers – the latest leak from the International Consortium of Investigative Journalists (ICIJ)? As you know, the ICIJ uses Neo4j to find the hidden connections in the vast numbers of files and data. They have now made the first data-release of that leak available and Michael Hunger dove right in.
Furthermore, this week is completely decked out with data science topics. We are exploring knowledge graphs with named entity recognition or text analyze Electronic Health Records. In addition to these two great articles we invite you to watch Clair’s video this week about Graph Embeddings.
Enjoy this week’s edition of Twin4j.
Andreas & Alexander
Ashleigh N. Faith – This Week’s Featured Community Member
Ashleigh specializes in multilingual search and behavioral analytics, focused on semantics, interoperability, and natural language, and realized through ontologies and knowledge graphs. Her domain focus is STEM subject matter – particularly in transportation, mechanical, medical, and electrical engineering technology. She’s worked on eCommerce, Business Intelligence, and Network Analysis data as well.
Ashleigh is an active member of the community and striving to educate others on the value, power, and importance of knowledge graphs. For this she was awarded the
Neo4j Graphie Award 2021. Congratulations Ashleigh!
Watch Ashleigh’s videos on YouTube:
Thanks a lot for all your great videos and your work for the graph community.
Digging Into the ICIJ Pandora Papers Dataset with Neo4j
Just a few days ago, the Pulitzer Award winning International Consortium of Investigative Journalists (ICIJ) published the first data-release of the recent Pandora Papers investigation. This time, the data publication was not split across the different investigations but contains the full offshoreleaks database in one dataset. This gives us the opportunity to explore the data of shell companies, law firms, banks, and ultimate owners across all leaks and investigations.
Dive into the data with Michael Hunger and find out how officers are related with Entities, Intermediaries, and Shell Companies.
How to Build a Knowledge Graph with Neo4j and Transformers
Learn from Walid Amamou how to build a knowledge graph from job descriptions using fine-tuned transformer-based
Named Entity Recognition (NER) and spacy’s relation extraction models. The method described here
can be used in many different fields such as biomedical, finance, healthcare, and beyond.
Exploring Electronic Health Records with MedCAT and Neo4j
Zeljko gives a hands-on tutorial on making biomedical concepts extracted from free text easily accessible to clinicians and researchers.
Biomedical NER+L is concerned with extracting concepts from free text found in Electronic Health Records (EHRs) and linking them to large biomedical databases like SNOMED-CT and UMLS. In this post, Zeljko focuses on what to do once concepts are extracted from free text – in other words, how to make them useful to clinicians and other researchers.
Bite-Sized Neo4j for Data Scientists
Clair Sullivan has added more videos to her great video series with short overview videos for Data Scientists. Her recent addition is episode 17 and she goes into “Creating FastRP Graph Embeddings.”
Neo4j Connections: Graphs for Cloud Developers
December 15, 2021: 7:30 a.m. – 11:30 a.m. PT | 15:30 – 19:30 GMT
December 16, 2021: 9:00 a.m. IST | 11:30 a.m. SGT/HKT/CST | 12:30 p.m. JST | 2:30 p.m. AEDT
Join us for a half-day virtual event and discover why graphs can revolutionize your application, and how Neo4j in the cloud can solve your needs faster, better, and simpler. You’ll enjoy technical talks from our experts and see real-world users showcasing their projects, so you’ll have everything you need to get started right away.
Don’t forget to RT if you liked it too!