Automated Verbal-Pattern Extraction from Political News Articles using CAMEO Event Coding Ontology
Erick Skorupa Parolin, Sayeed Salam, Latifur R. Khan, Patrick T. Brandt, Jennifer S. Holmes · 2019
Structured metadata extraction from raw-text in different domains is gaining strong attention from the research communities and offering good applicable scenarios. In Political Science, these metadata play a significant role in studying and predicting intra-and inter-state relationships and often follows a certain structural representation. Our work exploits CAMEO (Conflict and Mediation Event Observations) ontology to extract events from political news articles. This event will be represented by metadata such as who-did-what-to-whom format. We face a number of challenges in this extraction process due to the incompleteness of CAMEO dictionaries. In particular, for some verb patterns appeared in articles we may not find a appropriate match in CAMEO verb dictionary (i.e "what"). Our goal is to recommend new verb patterns by mining a large number of news articles to enhance the existing CAMEO verb dictionaries. For this, first we apply Association Rule Mining to find frequent verb patterns. Next, to assign categories of these verb patterns, we develop a novel algorithm based on Word-to-Vec model. Finally, we develop a prototype system for automatically recommending a number of useful verb patterns.