Half-day, hands-on workshop on AI-powered social media analytics using multimodal embeddings and knowledge graphs in Neo4j. Participants will use a curated Twitter/X-style dataset to build AI agents that utilize vector search and graph structures for in-depth analysis. Prior tutorial context:
https://github.com/xbwei/data-analysis-with-generative-aiThis workshop requires registration -
click here to registerAbstractBuilding on the instructor’s earlier workshops on generative AI in social analytics (see: https://github.com/xbwei/data-analysis-with-generative-ai), this hands-on session introduces participants to advanced techniques in multimodal embeddings and Agent-Based Knowledge Graphs. While previous versions focused on flat storage (e.g., MongoDB), this workshop emphasizes the need to model social data as a connected network that AI Agents can use for reasoning and analysis.
To maximize learning time, the workshop uses curated, pre-packaged datasets. This enables participants to bypass API restrictions and focus directly on analytics. Participants will learn how to organize social data into a Neo4j knowledge graph, representing users, posts, and interactions as interconnected nodes instead of isolated documents.
The core of the workshop examines the intersection of Agentic AI and Network Science. Attendees will create high-dimensional vector embeddings for text and images using modern embedding models and store them directly within graph nodes. This allows the development of Graph-Augmented AI Agents—systems capable of performing semantic vector searches and navigating the graph network to retrieve context. By combining these technologies, researchers can build agents that synthesize insights from connected nodes, enabling more nuanced detection of communities and misinformation than traditional methods.
By the end of the session, attendees will gain practical skills in:
- Graph Database Foundations: Setting up a Neo4j database and importing social data structures (Nodes & Edges).
- Multimodal Embeddings: Creating and saving vector embeddings for text and images within the graph to facilitate semantic search.
- Agent-Based Reasoning: Developing agent workflows that leverage vector retrieval and graph traversal to enable evidence-based analysis.
