learned_hands_traffic

Classify if a user post implicates legal isssues related to traffic.

---

Source: Learned Hands

License: CC BY-NC-SA 4.0

Size (samples): 562

Legal reasoning type: Issue-spotting

Task type: Binary classification

Task description

This is a binary classification task in which the model must determine if a user’s legal post discusses problems with traffic and parking tickets, fees, driver’s licenses, and other issues experienced with the traffic system. It also concerns issues with car accidents and injuries, cars’ quality, repairs, purchases, and other contracts.

Task construction

This task was constructed from the LearnedHands dataset. Please see their website for more information on annotation. Our task consists of a binarized version of the original dataset, with “negatives” randomly sampled from posts with other topics. This dataset is class balanced.