Information Extraction (IE) is the first step of this process. It attempts to make the text's semantic structure explicit by analysing text and identifying mentions of semantically defined entities and relationships within it. These relationships can then be recorded in a database to search for a particular relationship or to infer additional information from the explicitly stated facts. Moreover, once "basic" data structures like tokens, events, relationships, and references are extracted from the text provided, related information can be extended by introducing new sources of knowledge like ontologies (ConceptNet 5, WordNet, DBpedia, domain specific ontology) or further processed/extended using services like AlchemyAPI.

This session will highlight Neo4j as a viable tool in an NLP ecosystem demonstrating that it offers not only a suitable model for representing such complex data but also providing efficient ways for navigating this data. Dr. Negro will talk about features that allow the creation of advanced services on top of text analysis: recommendations, trend discovery, and finding influencers. In particular, the GraphAware NLP project will be presented as example in this direction. It is an open source Neo4j plugin that integrates NLP processing capabilities (provided by StanfordNLP and other NLP software) and existing ontology data sources (such as ConceptNet 5 and Wordnet) leveraging the power of Neo4j as backend engine

In this talk you will discover how this amount of user activities transformed in a suitable graph can become a new source of knowledge.

A demonstration of how Neo4j and machine learning algorithms built on top of it can leverage this tremendous amount of hidden valuable real-time data to gain new insights, offering new application possibilities, from recruitment to social network analysis and recommendations.

The talk will cover topics like data pipelines to Neo4j, technical challenges, algorithms and application ideas you can build around this kind of platforms.