Deep Active Learning for Data Mining from Conflict Text Corpora
This addresses the workload issue for researchers and organizations collecting high-resolution conflict data, though it is incremental as it applies an existing method (active learning) to a specific domain.
The paper tackles the problem of extracting detailed conflict dynamics (e.g., targets, tactics) from text corpora, which is labor-intensive, by proposing a deep active learning approach that reduces required human annotation by up to 99% while achieving performance similar to human coding.
High-resolution event data on armed conflict and related processes have revolutionized the study of political contention with datasets like UCDP GED, ACLED etc. However, most of these datasets limit themselves to collecting spatio-temporal (high-resolution) and intensity data. Information on dynamics, such as targets, tactics, purposes etc. are rarely collected owing to the extreme workload of collecting data. However, most datasets rely on a rich corpus of textual data allowing further mining of further information connected to each event. This paper proposes one such approach that is inexpensive and high performance, leveraging active learning - an iterative process of improving a machine learning model based on sequential (guided) human input. Active learning is employed to then step-wise train (fine-tuning) of a large, encoder-only language model adapted for extracting sub-classes of events relating to conflict dynamics. The approach shows performance similar to human (gold-standard) coding while reducing the amount of required human annotation by as much as 99%.