Neo4j Graph Data Science 1.5: Exploring the Speaker-Listener LPA Overlapping Community Detection Algorithm

By Mark Needham - 2021-02-09

Description

In this post we'll explore the Speaker Listener LPA overlapping community algorithm that was added to the Neo4j Graph Data Science Library in version 1.5.0.

Summary

  • Connected to Neo4j 4.2.0 at neo4j://localhost:7687 as user neo4j.
  • neo4j@neo4j> {"user":{"followers":2793,"following":1121,"name":"Synechron","bio":"Synechron is a leading Digital IT Consulting firm Accelerating Digital initiatives for banks, asset managers & insurance companies around the world.
  • The algorithm does compute an association strength score per node per community, but that score isn’t returned (at least at the moment!).
  • One way is to use this algorithm to work out which users to follow to learn about other communities.

 

Topics

  1. Database (0.27)
  2. Stock (0.14)
  3. UX (0.08)

Similar Articles

HDBSCAN Clustering with Neo4j

By Medium - 2021-01-15

I recently came across the article “How HDBSCAN works” by Leland McInnes, and I was struck by the informative, accessible way he explained…

kdn251/interviews

By GitHub - 2020-09-30

Everything you need to know to get the job. Contribute to kdn251/interviews development by creating an account on GitHub.

QuickGraph#17 The English WordNet in Neo4j (part 2)

By Jesús Barrasa - 2021-02-05

In this second post on WordNet on Neo4j I will be focusing on querying and analysing the graph that we created in the previous post. I'll leave for a third one more advanced analysis and integrations ...