JLCL Special Issue on Offensive Language
Call for Papers
Recent years have seen a sharp uptick in studies of offensive language (and related notions such as abusive language, hate speech, verbal aggression etc.) as well as of patterns of online behavior such as cyberbullying and trolling. Multiple efforts have been launched for the exploration of computational approaches and the establishment of benchmark datasets for various languages (Bosco et al. 2018; Wiegand et al. 2018; Zampieri et al. 2019; Basile et al. 2019; inter alia).
In this research, the inventory of categories used to classify units of text varies significantly across different papers and shared tasks. The most common division is between offensive language (or abuse or hate etc.) and a neutral or other class. Beyond binary classification, there are several ways to deepen the analysis. One of them consists in subdividing the overall offense class according to the targeted group, distinguishing, for instance, sexism and racism from a neither class (Waseem and Hovy 2016). Another way of adding detail to the analysis is to distinguish sub-classes of offensive language. The 2018 GermEval Shared Task on Offensive Language (Wiegand et al. 2018), for instance, included a fine-grained task that split up offensive language into the three sub-classes abuse, insult and profanity. A third option is to use a numeric measure of offensiveness (Ross et al. 2016), foregoing class labels. Yet another dimension along which offensive language can be subdivided is the distinction between explicit and implicit cases (Waseem et al.2017; Gao et al 2017).
In addition to the issue of how the task is to be formulated, there exists a wide and rapidly evolving set of computational approaches for performing the chosen classification. Schmidt and Wiegand 2017 give a useful recent overview of the state of the art, also providing among other things an extensive discussion of feature-based classification. Wiegand et al. 2018 report that for the GermEval 2018 Shared Task feature-based supervised learning was competitive, even though many neural systems participated and performed well.
Beyond the recognition of offensive language, research in a computational social science setting has begun to study who produces offensive language on particular platforms under which conditions (for instance, Wulczyn et al. 2017 for Wikipedia). And finally, the work on offensive language recognition itself has raised questions of ethics and bias (Dixon et. al 2018).
This special issue is open to authors interested in automatic classification of offensive language on the internet. While we guest editors came to this special issue by way of the past and the ongoing GermEval shared tasks, we would like to attract a broad range of submissions.
We invite submissions describing novel work on any aspect related to the general scope of the special issue. Note that the special issue is not limited to any particular human language.
The topics of interest include, but are not limited to, the following
- Annotation schemes for offensive language
- Annotated corpora
- Evaluation methodology for offensive language
- Bias and ethical concerns in offensive language detection
- Distinguishing use of offensive language from mention or reports of offensive language
- Offensive language directed towards individual target groups (e.g. sexism, antisemitism)
- Detecting the targets of offensive language
- Offensive utterances in their pragmatic and socio-linguistic context
- Distinguishing explicit from implicit offensive language
- Offensive language in diverse settings beyond Twitter and Facebook
- Multilingual aspects: exploiting multilingual resources and corpora
- Methods and approaches for building lexical resources for offensive language detection
JLCL – Journal of Language Technology and Computational Linguistics – is an online-only peer-reviewed journal supported by the German Society for Computational Linguistics and Language Technology (GSCL).
How to submit
The submitted papers will undergo peer review process before they can be accepted. To facilitate the review process, we request you to send a letter of intent (2 pages maximum) explaining the contents of your intended submission by September 1, 2019. Please send your letter of intent to the guest editors via JLCL_SIOL2020@googlegroups.com. You will receive an email confirmation within a week. Instructions for submission of full papers (15-20 pages) will be sent by email, September 20, 2019.
Submission of full articles will be due December 15, 2019. Notification of acceptance will be communicated as we progress with the review process.
Josef Ruppenhofer – Institute for German Language, Mannheim
Melanie Siegel – University of Applied Sciences, Darmstadt
Julia Maria Struß – University of Applied Sciences, Potsdam
Guest Editorial Board
 Basile, Valerio, Cristina Bosco, Viviana Patti, Manuela Sanguinetti, Elisabetta Fersini, Debora Nozza, Francisco Rangel, Paolo Rosso. Multilingual detection of hate speech against immigrants and women in Twitter (hatEval). SemEval 2019 Task 5.
 Cristina Bosco, Felice Dell’Orletta, Fabio Poletto, Manuela Sanguinetti, and Maurizio Tesconi. Overview of the EVALITA 2018 hate speech detection task. In Proceedings of the Sixth Evaluation Campaign of Natural Language Processing and Speech
Tools for Italian. Final Workshop (EVALITA 2018) co-located with the Fifth Italian
Conference on Computational Linguistics (CLiC-it 2018), Turin, Italy, December
12-13, 2018., 2018.
 Lucas Dixon, John Li, Jeffrey Sorensen, Nithum Thain, and Lucy Vasserman. Measuring and mitigating unintended bias in text classification. In Proceedings of the
2018 AAAI/ACM Conference on AI, Ethics, and Society, AIES ’18, pages 67–73,
New York, NY, USA, 2018. ACM.
 Lei Gao, Alexis Kuppersmith, and Ruihong Huang. Recognizing explicit and implicit
hate speech using a weakly supervised two-path bootstrapping approach. In Proceedings of the Eighth International Joint Conference on Natural Language Processing, IJCNLP 2017, Taipei, Taiwan, November 27 - December 1, 2017 - Volume 1: Long Papers, pages 774–782, 2017.
 Amir H. Razavi, Diana Inkpen, Sasha Uritsky, and Stan Matwin. Offensive language
detection using multi-level classification. In Proceedings of the 23rd Canadian Conference on Advances in Artificial Intelligence, AI’10, pages 16–27, Berlin, Heidelberg, 2010. Springer-Verlag.
 Björn Ross, Michael Rist, Guillermo Carbonell, Ben Cabrera, Nils Kurowsky, and
Michael Wojatzki. Measuring the Reliability of Hate Speech Annotations: The Case
of the European Refugee Crisis. In Michael Beißwenger, Michael Wojatzki, and Torsten Zesch, editors, Proceedings of NLP4CMC III: 3rd Workshop on Natural Language Processing for Computer-Mediated Communication, pages 6–9, 2016.
 Anna Schmidt and Michael Wiegand. A survey on hate speech detection using
natural language processing. In Proceedings of the Fifth International Workshop on Natural Language Processing for Social Media, pages 1–10, Valencia, Spain, April 2017. Association for Computational Linguistics.
 Zeerak Waseem, Thomas Davidson, Dana Warmsley, and Ingmar Weber. Under-
standing abuse: A typology of abusive language detection subtasks. In Proceedings
of the First Workshop on Abusive Language Online, pages 78–84, Vancouver, BC,
Canada, August 2017. Association for Computational Linguistics.
 Zeerak Waseem and Dirk Hovy. Hateful symbols or hateful people? predictive features for hate speech detection on twitter. In Proceedings of the Student Research
Workshop, SRW@HLT-NAACL 2016, The 2016 Conference of the North American
Chapter of the Association for Computational Linguistics: Human Language Technologies, San Diego California, USA, June 12-17, 2016, pages 88–93, 2016.
 Michael Wiegand, Melanie Siegel, and Josef Ruppenhofer. Overview of the GermEval
2018 shared task on the identification of offensive language. Proceedings of GermEval
2018, 14th Conference on Natural Language Processing (KONVENS 2018), Vienna,
Austria – September 21, 2018, pages 1 – 10. Austrian Academy of Sciences, Vienna,
 Michael Wiegand, Josef Ruppenhofer, Thomas Kleinbauer: Detection of abusive language: The problem of biased datasets. In: Proceedings of the 2019 Annual Conference of the North American Chapter of the Association for Computational Linguistics, June 2-7, 2019, Minneapolis, USA, 2019, (to appear).
 Michael Wojatzki, Tobias Horsmann, Darina Gold, and Torsten Zesch. Do Women
Perceive Hate Differently: Examining the Relationship Between Hate Speech, Gender, and Agreement Judgments. In Proceedings of the Conference on Natural Language Processing (KONVENS), pages 110–120, Vienna, Austria, 2018.
 Ellery Wulczyn, Nithum Thain, and Lucas Dixon. Ex machina: Personal attacks
seen at scale. In Proceedings of the 26th International Conference on World Wide Web, WWW’17, pages 1391–1399, Republic and Canton of Geneva, Switzerland, 2017. International World Wide Web Conferences Steering Committee.
 Zampieri, Marcos and Malmasi, Shervin and Nakov, Preslav and Rosenthal, Sara and Farra, Noura and Kumar, Ritesh. SemEval-2019 Task 6: Identifying and Categorizing Offensive Language in Social Media (OffensEval). arXiv preprint arXiv:1903.08983, 2019.