NEATCLasS was held for the first time in 2022, co-located at ICWSM 2022, on 6th June 2022, in a hybrid format - in Atlanta, Georgia (US) and online.

Papers were published in the Proceedings of the ICWSM Workshops.

Program

Tentative Timeline

The workshop is a full-day meeting and will be held on 6th June 2022 in hybrid mode. This schedule is tentative and will be finalised in the coming days.

All times shown below are in EDT.

Accepted Papers

Janina S. Pohl, Dennis Assenmacher, Moritz V. Seiler, Heike Trautmann, & Christian Grimme. Artificial Social Media Campaign Creation for Benchmarking and Challenging Detection Approaches

Chiyu Zhang, Muhammad Abdul-Mageed, & El Moatez Billah Nagoudi. Decay No More: A Persistent Twitter Dataset for Learning Social Meaning — Winner of the best paper award

Viktor Schlegel, Erick Mendez-Guzman, & Riza Batista-Navarro. Towards Human-Centred Explainability Benchmarks For Text Classification

Paula Reyero Lobo, Martino Mensio, Angel Pavon Perez, Vaclav Bayer, Joseph Kwarteng, Miriam Fernandez, Enrico Daga, & Harith Alani. Estimating Ground Truth in a Low-labelled Data Regime: A Study of Racism Detection in Spanish

Interactive Paper Presentations

While all the authors of accepted papers will have the chance to record a 20 min presentation of their work that will be published on the workshop website ahead of time, live presentations will be designed to promote interaction. To give space to fresh ideas, participants will be invited to trial an innovative format for paper presentations: presenters will be given 5 minutes to describe their research questions and hypothesis, and a group discussion will start after that (10 minutes). The goal is to give time to the audience to fully appreciate the complexity of the issue targeted in the paper, and propose ideas that have not been biased from the authors’ approach. At the end of the discussion, presenters will be given 5 more minutes to describe their method and results, followed by a new group discussion about the interpretation and implications of such results (10 min).

Challenge

In the afternoon we will kick off with a small challenge: participants will be divided into groups and asked to come up with hard examples that trick existing text classifiers. To this end, we will provide an interactive model for the detection of abusive language and we will invite participants (in advance) to provide their own models and tasks for collaborative adversarial testing. The challenge will work as a warm-up session for the following group activity.

Resources for the challenge are available here.

Group Activity

This last session is meant to bring researchers together and discuss their experience with the evaluation of both models and human annotations. The goal is to collect ideas for new evaluation approaches and future work in the field and to discuss how we should organise competitions when there are multiple evaluation metrics and benchmarking datasets are dynamic. Depending on the number of participants, we will break up into small groups that reconvene after a coffee break to report resulting ideas.

Keynote 1: Isabelle Augenstein

Isabelle Augenstein

Isabelle Augenstein is an Associate Professor at the University of Copenhagen, Department of Computer Science, where she heads the Copenhagen Natural Language Understanding research group as well as the Natural Language Processing section. Her main research interests are fact checking, low-resource learning, and explainability. Prior to starting a faculty position, she was a postdoctoral researcher at University College London, and before that a PhD student at the University of Sheffield. She currently holds a DFF Sapere Aude Research Leader fellowship on ‘Learning to Explain Attitudes on Social Media’, and is a member of the Young Royal Danish Academy of Sciences and Letters.

Keynote 2: Munmun De Choudhury

Munmun De Choudhury

Munmun De Choudhury is an Associate Professor of Interactive Computing at Georgia Tech. Dr. De Choudhury is best known for laying the foundation of a new line of research that develops computational techniques towards understanding and improving mental health outcomes, through ethical analysis of social media data. To do this work, she adopts a highly interdisciplinary approach, combining social computing, machine learning, and natural language analysis with insights and theories from the social, behavioral, and health sciences. Dr. De Choudhury has been recognized with the 2021 ACM-W Rising Star Award, 2019 Complex Systems Society – Junior Scientific Award, numerous best paper and honorable mention awards from the ACM and AAAI, and features and coverage in popular press like the New York Times, the NPR, and the BBC. Dr. De Choudhury currently serves on the Board of Directors of the International Society for Computational Social Science and on the Steering Committee of the International Conference on Web and Social Media, the leading conference on interdisciplinary studies of social media. Earlier, Dr. De Choudhury was a faculty associate with the Berkman Klein Center for Internet and Society at Harvard, a postdoc at Microsoft Research, and obtained her PhD in Computer Science from Arizona State University.

Keynote 3: Zeerak Talat

Zeerak Talat

Zeerak Talat is a post-doctoral fellow at the Digital Democracies Institute at Simon Fraser University. Talat's research focuses on the foundational limitations and the ethics of machine learning and NLP technologies as viewed through content moderation and social predication tasks. Talat received a Ph.D. from the University of Sheffield. During this time, Talat worked on automated content moderation and how the practice of automating content moderation using machine learning revealed the underlying political economy of machine learning, displaying issues of access, equality, and ethical practices. Talat also founded and runs the Workshop on Online Abuse and Harms (WOAH), which focuses on the technical and social developments of automated content moderation infrastructure. Talat’s current work aims to identify the specific underlying causes for why and how machine learning comes to be enacted as a marginalizing technology.

Programme Committee

Programme Committee members: