Call for Papers and Shared Tasks

As the number of users and their web-based interaction has increased, incidents of verbal threat, aggression and related behavior like trolling, cyberbullying, and hate speech have also increased manifold globally. Such incidents of online abuse have not only resulted in mental health and psychological issues for users, but they have manifested in other ways, spanning from deactivating social media accounts to instances of self-harm and suicide and offline violence as well. To mitigate these issues, researchers have begun to explore the use of computational methods for identifying such toxic interactions online. In particular, Natural Language Processing (NLP) and ML-based methods and more recently Large Language Models (LLMs) have shown great promise in dealing with such abusive behavior through early detection of inflammatory content.

We understand that a synergy and mutual cooperation needs to be established between the linguistic analysis of impolite, threatening, aggressive and hateful language (from pragmatic, sociolinguistic, discourse analysis and other perspectives) and NLP and ML (including deep learning) - based approaches to identification of such languages. As such we actively focus on bringing the two communities together to develop a better understanding of these issues. The workshop provides a forum for everyone working in the area to discuss their research and for further collaboration.

Linguistic Theories, Analysis and Models

• Theories and models of aggression and conflict in language. 

• Grammar of hate, impoliteness and aggression incl phonological and morphosyntactic properties

• Pragmatic and Discourse Analysis of impolite, aggressive and hateful language

• Sociolinguistic analysis of impolite, aggressive and hateful language

• Corpus-based analysis of impolite, aggressive and hateful language

• Cognitive and Psycholinguistic Studies of hate and aggression.

• Online Aggression and Physical Harm

• Cyberbullying, threatening, hateful, aggressive and abusive language on the web.

• Multilingualism and aggression.

• Multimodality and aggression

Resource Development and Computational Modelling

• Resource Development - Corpora, Annotation Guidelines, Standards and Best Practices for threat and aggression detection.

• Detection of threats and bullying on the web - data collection methodologies and approaches.

• Crowdsourcing and resource development for threatening, aggressive and hateful language.

• Replicability and Reproducibility of resources for aggression, hate speech and offensive language detection.

• Inter-annotator agreement, Perspectivist Datasets and Issues with traditional methods of annotation.

• Annotation Tools and Infrastructure for working on threatening, aggressive and hateful language.

• Computational Models and Methods for aggression, hate speech and offensive language detection in text and speech.

• Aggressive and Offensive Language Detection in and through Large Language Models (LLMs).

• Methods of building diverse, multilingual and multimodal resources and models with a focus on under-resourced languages.

• Evaluating and benchmarking resources and models for aggression, hate speech and offensive language detection

• Automatic censorship and moderation: ethical, legal and technological issues and challenges.

Describing your LRs in the LRE Map is now a normal practice in the submission procedure of LREC (introduced in 2010 and adopted by other conferences). To continue the efforts initiated at LREC 2014 about “Sharing LRs” (data, tools, web-services, etc.), authors will have the possibility, when submitting a paper, to upload LRs in a special LREC repository. This effort of sharing LRs, linked to the LRE Map for their description, may become a new “regular” feature for conferences in our field, thus contributing to creating a common repository where everyone can deposit and share data.

As scientific work requires accurate citations of referenced work so as to allow the community to understand the whole context and also replicate the experiments conducted by other researchers, ELRA encourages all LREC-COLING authors to endorse the need to uniquely identify LRs through the use of the International Standard Language Resource Number (ISLRN, www.islrn.org), a Persistent Unique Identifier to be assigned to each Language Resource. The assignment of ISLRNs to LRs cited in LREC-COLING 2024 papers will be offered at submission time.