Workshop on Computational Approaches to Subjectivity, Sentiment & Social Media Analysis

Subjectivity, Emotion and Sentiment Analysis

12th Workshop on Computational Approaches to Subjectivity, Sentiment & Social Media Analysis

The 12th edition of WASSA is collocated with ACL 2022

Important dates

Background and Envisaged Scope

Starting with reviews on products on e-commerce sites and ending with the emotional effect presentin or intended by media coverage, research in automatic Subjectivity and Sentiment Analysis as wellas explicit and implicit Emotion Detection and Classification has flourished in the past years. Theimportance of the field has been proven by the high number of approaches proposed in research in thepast decade, as well as by the interest it generated in other disciplines, such as Economics, Sociology,Psychology, Marketing, Crisis Management Digital Humanities. Building on previous editions, the aim of WASSA 2022 is to bring together researchers workingon Subjectivity, Sentiment Analysis, Emotion Detection and Classification and their applications toother NLP or real-world tasks (e.g. public health messaging, fake news, media impact analysis, socialmedia mining, computational literary studies) and researchers working on interdisciplinary aspectsof affect computation from text. For this edition, we encourage the submission of long and shortresearch and demo papers including, but not restricted to the following topics:

Paper Submission

At WASSA 2022, we will accept three types of submissions: For the regular research track we accept long & short papers:

Submissions can be done through ARR (see the ARR CFP guidelines) or alternatively directly through our OpenReview website. For more information about templates, guidelines, and instructions, check the ARR Call for Papers.

New this year is that we also introduce an industry track, for which we accept demo papers:

Additionally, system description papers from the shared task will be presented either orally or as poster.

Shared-Task: Empathy Detection and Emotion Classification

Emotion is a concept that is challenging to describe. Yet, as human beings, we understand the emotional effect situations have or could have on us and other people. How can we transfer this knowledge to machines? Is it possible to learn the link between situations and the emotions they trigger in an automatic way?

We propose the Shared Task on Empathy Detection, Emotion Classification and Personnality Detection, organized as part of WASSA 2022 at ACL 2022. This task aims at developing models which can predict empathy and emotion based on essays written in reaction to news articles where there is harm to a person, group, or other.

Important dates:

For further details on the shared task and how to participate, visit the codalab website:

Invited Speakers



Dr. Jeremy Barnes

Dr. Jeremy Barnes is an assistant professor at the University of the Basque Country UPV/EHU and a member of the IXA NLP group. He holds a PhD in computational linguistics from Pompeu Fabra University in Barcelona on Cross-lingual Sentiment Analysis for Under-resourced Languages. His research focuses on creating resources and NLP models for under-resourced languages and scenarios, including cross-lingual methods, weak supervision, multi-task learning, and domain adaptation, and he has worked extensively on sentiment and emotion analysis.

Prof. dr. Orphée De Clercq

Prof. dr. Orphée De Clercq is assistant professor of language technology for educational applications at the LT3 Language and Translation Technology Team of Ghent University. She has extensive experience in deep semantic processing of natural language, readability prediction and text mining of (subjective) user-generated content using machine learning techniques. Regarding the latter she has explored new techniques for aspect-based sentiment analysis, ported this pipeline to different domains and languages and successfully finalized a valorization project with the industry. Currently, she is also looking into implicit sentiment analysis and emotion detection. She has published in some of the leading NLP conferences and journals and has co-organised several shared tasks on sentiment analysis in the past.

Dr. Valentin Barriere

Dr. Valentin Barriere is a PostDoc researcher at the European Commission’s Joint Research Center of Ispra. During his PhD, he worked on affective phenomena detection in oral interaction. He mainly worked with graphical discriminative models using features leveraging the robustness and the high accuracy of Machine Learning algorithms with the fine-grained modeling of linguistic rules. He is now working on multilingual sentiment analysis and multimodal content analysis.

Dr. Shabnam Tafreshi

Dr. Shabnam Tafreshi is an assistant research scientist at University of Maryland, Applied Re-search Lab for Intelligence and Security. Research interests: computational semantic understanding across languages. She is working towards improving NLP models to better extract knowledge from text by complementing NLP models with meaning constructs. Better models are needed for down-stream tasks in text classification and knowledge extraction. In addition, her research is focused on methodologies for collecting and annotating quality data for building robust NLP models.

Dr. Sawsan Alqahtani

Dr. Sawsan Alqahtani is an applied scientist in Amazon Web Services, developing leading AI technologies. She obtained her PhD in Computer Science from George Washington University (2019). Her thesis focuses on the development of full and partial diacritic restoration and its impact on down-stream applications. Her research interests include the development of cross-lingual and multilingual models, especially in low resource settings for different NLP tasks, including conversational agents.

Prof. dr. João Sedoc

Prof. dr. João Sedoc is an assistant professor of Technology in the Technology, Operations and Statistics department at New York University. He holds a PhD in computer science from the University of Pennsylvania on Building and Evaluating Conversational Agents (2019). His research focuses on conversational agents with a keen interest in understanding empathy and emotion andapplying these models to improve conversational agents. He has published in some leading NLPconferences and co-organised several workshops in the past.

PD Dr. Roman Klinger (he/him)

is a senior lecturer at the Institute for Natural Language Processing (IMS) at the University of Stuttgart. He studied computer science with a minor in psychology, holds a Ph.D. in computer science from TU Dortmund University (2011), and received the venia legendi in computer science in Stuttgart (2020). Before moving to Stuttgart, he worked at the University of Bielefeld, at the Fraunhofer Institute for Algorithms and Scientific Computing, and the University of Massachusetts Amherst. Roman Klinger’s vision is to enable computers to understand and generate text regarding both factual and non-factual information. This finds application in inter-disciplinary research, including biomedical text mining, digital humanities, modelling psychological concepts (like emotions) in language, and social media mining. He co-organized several workshopsin the past, including two editions of WASSA.

Dr. Alexandra Balahur

Dr. Alexandra Balahur is scientific officer at the European Commission’s Joint Research Centrein Ispra, Italy. She holds a PhD in Computer Science, obtained with the thesis entitled “Methodsand Resources for Sentiment Analysis in Multilingual Documents of Different Text Types” (2011). Her main fields of interest are sentiment analysis (opinion mining), emotion detection, informationextraction and textual entailment. She is the author of over 80 scientific publications, in journals and conference proceedings. She has been the main organizer of the WASSA workshops.