This Week in Neo4j: Website Analysis, Conversational AI, Graph Machine Learning, Facial Recognition, Graph Tutorial, and More

In this week’s newsletter, you can read about constructing a real-time interactive conversational AI system. Antonio Origlia describes how graphs make it possible to cross-reference encyclopedic knowledge and dialogue corpora, representing both the domain knowledge and the way people communicate about it.

If ML topics are on your New Year’s list of study resolutions, there are a couple of other articles to check out – like the NLP pipeline constructed by Tomaz Bratanic and an improved facial recognition system by Sefik Ilkin Serengil.

Yolande Poirier

P.S.: If you’re a developer building modern applications with GraphQL, don’t forget to take this short, two-minute survey. We want to hear from you!

Vlasta Kůs is a machine learning, deep learning, and natural language processing enthusiast. His background is in particle physics research with 10+ years of experience in software development and data science. He specializes in using machine learning for building knowledge graphs from unstructured data. You can follow him on LinkedIn.

In his NODES 2022 presentation, he covers the use case of building a knowledge graph for the archive of a major foundation to help empower researchers (or business analysts) to access previously unavailable levels of insight. Watch it now!

KNOWLEDGE GRAPH: Analyze Your Website With NLP
Tomaz Bratanic implements an NLP pipeline to parse a website for useful, unstructured data to construct a knowledge graph. Analyses of website network, link, keyword, and co-occurrence topic clustering are all thoroughly documented with code and links to Jupyter notebooks.
AI: Conversational Artificial Intelligence With Neo4j and the Unreal Engine – Part 1
Antonio Origlia describes how Real-Time Interactive 3D applications powered by the Unreal Engine are using graph database technology to enable the representation and investigation of knowledge. This blog is based on research conducted in the field of Embodied Conversational Agents (ECAs) at the URBAN/ECO Research Centre of Federico II University in Naples.
NODES SESSION: Take Data to the Next Level With Graph Machine Learning

Joinal Ahmed from Google and Chaitra Ravada from Twitter discuss why graph machine learning makes more sense than the traditional ML approach. They show you how graph ML powers use cases like recommendation systems, fraud detection, and more.

ML: How to Find False Positives in Facial Recognition With Neo4j

Sefik Ilkin Serengil improves a facial recognition model by combining deepfake and Neo4j. With FaceNet facial recognition model and MtCnn face detector, he uses the graph data science betweenness centrality algorithm to drop false positives among deepface verified pairs.

TOOL: Manage EoLs Like a Boss With

In this series installment, Adrien Sales builds an Neodash interface with product lifecycle data. Once imported into Neo4j, he runs Cypher queries to report apps that rely on deprecated Java.

TUTORIAL: A Simple Guide to Get Started With Graph Databases

In this technical overview and tutorial, Meet Shah shows you how to get started with graph databases. You’ll learn how to install Neo4j and how to derive useful insights from your data.


Don’t forget to retweet, if you like it!

    •  The new Neo4j extension for VS Code allows you to add multiple connections and run Cypher straight from a file or your current text selection. Learn about it.
    • neo4j-osmnx-experiments project works with OpenStreetMap data in Neo4j using OSMnx. This project uses Poetry to manage dependencies and Python virtual environments. Check it out.
    • Neo4j Java Driver Tool Belt project now consists of a read-only object mapper and a parameter renderer. The idea is to collect a bunch of tooling around the official Neo4j Java Driver. Learn more.
    •  Dairon Pérez Frías created a series video tutorials in Spanish about Neo4j. Kudos to Dairon! Discover his tutorials