[Corpora-List] GermEval 2021 Shared Task on the Identification of Toxic, Engaging, and Fact-Claiming Comments: Call for Participation

Wiegand, Michael Michael.Wiegand at aau.at
Thu Apr 15 17:42:47 CEST 2021

apologies for cross-posting

We are pleased to announce the *GermEval 2021 Shared Task on the Identification of Toxic, Engaging, and Fact-Claiming Comments*

This is the first call to participate in the shared task on the Identification of Toxic, Engaging, and Fact-Claiming Comments at GermEval 2021. We invite everyone from academia and industry to participate in the shared task. The workshop discussing the results of this shared task is planned to be held in conjunction with the Conference on Natural Language Processing (KONVENS) in September 2021.

*Introduction* The demand for approaches to identify harmful user content online is unchanged while the research field of Natural Language Processing is constantly evolving. The two previous GermEval shared tasks on the identification of offensive language (Struß et al., 2019; Wiegand et al., 2018) mark important references for research teams from both science and industry that use the datasets to evaluate their frameworks. With this year's shared task, we want participants to go beyond the identification of offensive comments. To this end, we extend the focus to two other classes of comments that are highly relevant to moderators and community managers on on-line discussion platforms: engaging comments and fact-claiming comments, meaning comments that should be considered as a priority for fact-checking. This shift aims to bridge the gap between the theoretical view on comment classification and the practical needs of discussion moderators.

*Data* The data comprise Facebook user comments. The complete dataset consists in total of more than 3,000 examples. Access to trial data will be granted upon registering for the task.

*Tasks* We offer the three following tasks. Participants in this year's shared task can choose to participate in any subset of subtasks.

Task 1: Toxic Comment Classification Task 2: Engaging Comment Classification Task 3: Fact-Claiming Comment Classification

More details on the subtasks (including examples) can be found at the website of the shared task (see link below).

*Important dates* Trial data ready: April 15, 2021 Training data release: April 30, 2021 Test data release: June 23, 2021 Submission deadline of system runs: June 30, 2021 Paper submission due: July 15, 2021 Camera ready due: August 10, 2021 KONVENS conference: September 6-10, 2021

*Website* https://germeval2021toxic.github.io/SharedTask/

*GermEval* GermEval is a series of shared task evaluation campaigns that focus on Natural Language Processing for the German language. GermEval has been conducted 6 times since 2014 in co-location with KONVENS/GSCL conferences.

*contact email* Please send any enquiry to the following email address: germeval2021toxic at gmail.com

Best regards,

Julian Risch (Hasso Plattner Institute, University of Potsdam) Anke Stoll (Department of Social Sciences, Heinrich Heine University Düsseldorf) Lena Wilms (Department of Social Sciences, Heinrich Heine University Düsseldorf) Michael Wiegand (Digital Age Research Center, University of Klagenfurt) -------------- next part -------------- A non-text attachment was scrubbed... Name: not available Type: text/html Size: 8673 bytes Desc: not available URL: <https://mailman.uib.no/public/corpora/attachments/20210415/6f958ef9/attachment.txt>

More information about the Corpora mailing list