APART: Automatic Political Actor Recommendation in Real-time

Extracting actor data from news reports is important when generating event data. Hand-coded dictionaries are used to code actors and actions. Manually updating dictionaries for new actors and roles is costly and there is no automated method. We propose a dynamic frequency-based actor ranking algorithm with partial string matching for new actor-role detection, based on similar actors in the CAMEO dictionary. This is compared to a graph-based weighted label propagation baseline method. Results show our method outperforms the alternatives.