Building and displaying name relations using automatic unsupervised analysis of newspaper articles

TL;DR

This paper introduces a tool that automatically recognizes names in news articles, infers inter-person relations through unsupervised analysis, and visualizes these relations on maps and graphs, aiding understanding of social networks.

Contribution

It presents an unsupervised method for extracting and visualizing inter-person relations from multilingual news data using a custom NER tool and large-scale clustering.

Findings

Successfully processed 15,000 articles daily in 15 languages

Built a knowledge base of co-occurrence statistics for persons

Enabled visualization of social relations on maps and graphs

Abstract

We present a tool that, from automatically recognised names, tries to infer inter-person relations in order to present associated people on maps. Based on an in-house Named Entity Recognition tool, applied on clusters of an average of 15,000 news articles per day, in 15 different languages, we build a knowledge base that allows extracting statistical co-occurrences of persons and visualising them on a per-person page or in various graphs.