Toward Automatically Identifying Legally Relevant Factors

In making legal decisions, courts apply relevant law to facts. While the typically changes slowly over time, facts vary from case case. Nevertheless, underlying patterns of fact may emerge. This research focuses on commonly present in cases where motorists are stopped for a traffic violation and subsequently detained while police officer conducts canine sniff vehicle drugs. We set fact, that is, factors suspicion, determining reasonable suspicion. demonstrate how these can be identified annotated annotations employed fine-tune transformer model identify previously unseen opinions.