Modeling Precursors for Event Forecasting via Nested Multi-Instance Learning
Yue Ning*, Virginia Tech; Sathappan Muthiah, Virginia Tech; Huzefa Rangwala, George Mason University; Naren Ramakrishnan, Virginia Tech
Forecasting large-scale societal events like civil unrest movements, disease outbreaks, and elections is an important and challenging problem. From the perspective of human analysts and policy makers, forecasting algorithms must not only make accurate predictions but must also provide sup-porting evidence, e.g., the causal factors related to the event of interest. We develop a novel multiple instance learning based approach that jointly tackles the problem of identifying evidence-based precursors and forecasts events into the future. Speciﬁcally, given a collection of streaming news articles from multiple sources we develop a nested multiple instance learning approach to forecast signiﬁcant societal events such as protests. Using data from three countries in Latin America, we demonstrate how our approach is able to consistently identify news articles considered as precursors for protests. Our empirical evaluation demonstrates the strengths of our proposed approach in ﬁltering candidate precursors, in forecasting the occurrence of events with a lead time advantage and in accurately predicting the characteristics of civil unrest events.