Competition

Online harassment is becoming prevalant as a specific communication type in Twitter. Considering the huge amount of user-genrated tweets each day, the problem of detecting and possibly limiting these contents automaticaaly in real time is becoming a fundamental problem specifically for female figures who have been harassed for a long time and Twitter was incapable of haleping them.

The proposed competition focusing of online harassment in Twitter in English. It has two related tasks: the first task is a binary classification to classify online harassment tweets versus not_harassment tweets, the second task is multi-class classification of online harassment tweets into three categories of "Indirect harassment", "sexual harassment" and "physical harassment".

• TASK A - Online Harassment Detection: In this task, tweets will be classify into two groups of harassment versus non-harassment.
• Task B- Categorizing of Different Types of Online Harassment Tweets: In this task, harassment tweets will be classified into three categries of "indirect harassment", "physical harssment" and "sexual harassment".

Important dates

• 1st of April 2019: Data and the forms (for getting dataset) will be provided.
• 23 of June- 25 of June 2019: Evaluation ends.
• 25 of June-28 of June 2019: Results are notified to participants.
• 28 of June-20 of July 2019: paper submission due.
• 30 of July 2019: papers reviews due.
• 1st of August 2019: Author notification.
• 20 of August 2019: Camera ready submission due.
• 16-20 of September 2019: ECML PKDD 2019.

Join the SIMAH mailing group: simah_competition_ecmlpkdd2019[at]googlegroups.com

Please note that the Google group will act as the main communication channel between the organizers and the participants.

IMPORTANT NOTE

Please fill in this questionnaire in order to obtain the dataset.

If you do not receive the dataset or have troubles accessing the data, let us know.

For more information regarding the competition please refer to the Codalab website:CodaLab-SIMAH

Organizers:

• Sima Sharifirad(Dalhousie University)

s.sharifirad@dal.ca

• Stan Matwin(Dalhousie University)