Knowledge-Based News Event Analysis and Forecasting

Abstract

In this talk, I will present our ongoing work at IBM Research on building a toolkit for news event analysis and forecasting. The toolkit is powered by a Knowledge Graph (KG) of events curated from structured and textual sources of event-related knowledge. The toolkit provides functions for 1) mapping ongoing news headlines to concepts in the KG, 2) retrieval, reasoning, and visualization for causal analysis and forecasting, and 3) extraction of causal knowledge from text documents to augment the KG with additional domain knowledge. Each function has a number of implementations using state-of-the-art neuro-symbolic techniques. I will go over a number of use cases for the toolkit, including use cases in finance and enterprise risk management.