Task B: "Threatening Language Detection in Urdu Tweets"

Task Description

With the growth of spread and importance of social media platforms, the effect of their misuse became more and more impactful. In particular, numerous posts contain threatening language towards certain users and hence worsen users’ experience from communication via such platforms and potentially put platform users in danger. The Urdu language has more than 230 million speakers worldwide with vast representation on social networks and digital media.

We encourage participants to suggest methods that can automatically detect threats in Urdu language to avoid violence and outrageous consequences.

Task B focuses on detecting Threatening language using Twitter tweets in Urdu language. This is a binary classification task in which participating systems are required to classify tweets into two classes, namely: (i) Threatening, and (ii) Non-Threatening.

1. Threatening - This Twitter post contains any threatening content.

2. Non-Threatening - This Twitter post does not contain any threatening or profane content.

Once the tweet is classified as "Threatening", then further classify the treat into two classes: (i) Group, and (ii) Individual.

3. Group - This Twitter post contains threatening content for group (s).

4. Individual - This Twitter post contains threatening or profane content for an individual.

We followed Twitter's definition to describe Threatening posts toward an individual or groups to threaten with violent acts, to kill or inflict serious physical harm, to intimidate, and to use violent language