THIRD WORKSHOP ON COMPUTATIONAL MODELING OF PEOPLE’S OPINIONS, PERSONALITY, AND EMOTIONS IN SOCIAL MEDIA

Workshop co-located with COLING - Barcelona

December 13, 2020

NEWS

• PEOPLES 2020 Proceedings are published in the ACL Anthology!
• Program is available!
• Accepted papers posted
• UPDATE: COLING’2020 IS GOING ENTIRELY VIRTUAL! All parts of the conference programme will involve a mixture of virtual presentations and real-time Q/A sessions. PEOPLES will be virtual also!
• IMPORTANT UPDATE: Please note that the workshop has been postponed to 13th December and the submission deadline is now extended, in accordance with COLING 2020 being postponed to December.
• Keynote: David Jurgens, University of Michigan, US
• The workshop will be held on December 13, 2020 at COLING in Barcelona

On social media, users nowadays freely express what is on their mind at any moment in time, at any location, and about virtually anything. These large amounts of spontaneously produced texts open up a unique opportunity to learn more about social media users, e.g., predicting socio-demographic variables (age, gender, profession, education), personality types, as well as emotions and opinion expressions. Indeed, this excellent opportunity has materialized in a large and growing number of recent workshops held at different Natural Language Processing, Artificial Intelligence, Semantic Web, and Information Retrieval venues, for example WASSA (focusing on sentiment and social media), PAN (focusing on author profiling like personality) and ESSEM (focusing on emotions in AI), including the organization of shared tasks such asat SemEval with a special sentiment track. However, such aspects of human personality and behavior have been mostly studied in isolation, often in different—but related—communities. PEOPLES aims at bringing these diverse communities a step closer to each other, to study people's traits and expressions jointly and in their interplay.

Indeed, the traits in the focus of PEOPLES can be seen as characterizing the whole person and should be studied together. Contextually, one should study how their interaction, and their computational modelling impact both natural language processing and society. This also in view of recent active discussions regarding ethical and bias-related aspects in NLP, which strongly relate to the traits that the PEOPLES workshop focuses on.

PEOPLES 2020 would be the continuation of successful editions that were held at COLING 2016 and NAACL 2018, by continuing to provide a forum for researchers who share an interest in personality, opinion and emotion detection, as well as the impact of this work on society.

We will encourage the submission of long (9 pages) and short (4 pages) research papers, including opinion statements. We will especially welcome views from different fields, and will welcome submissions related but not limited to the following topics:

• opinion, personality and emotion detection in social media
• opinions, personality and emotions and their interactions
• interaction between personality, opinion and emotions with socio-demographic variables
• interaction between personality, opinion and emotions and geo-spatial information
• interaction between socio-demographic, personality, opinion and emotions with politics
• analysis of social networks with attributes (e.g. socio-demographic attributes or opinions)
• modeling of personality, opinion and emotions from a multimodal perspective
• multilingual approaches to demographic inference from social media
• multilingual approaches to opinion, emotions and personality detection
• cross-cultural analysis of opinion, emotions, personality in multilingual social media data
• applications of predictive modeling of user traits
• bias-related issues, and the ethics of predictive modeling of user attributes

UPDATE: We also very much welcome research that focuses on how the usual PEOPLES dimensions might have changed or might be changing due to the special COVID-related circumstances. For example, how relevant traits might be represented differently now with respect to 'normal' times.

Keynote speakers

• David Jurgens (University of Michigan, US)

Accepted Papers

• Learning Emotion from 100 Observations: Unexpected Robustness of Deep Learning under Strong Data Limitations
  Sven Buechel, João Sedoc, H. Andrew Schwartz and Lyle Ungar
• HopeEDI: A Multilingual Hope Speech Detection Dataset for Equality, Diversity, and Inclusion
  Bharathi Raja Chakravarthi
• Red Is Open-Minded, Blue Is Conscientious: Predicting User Traits From Instagram Image Data
  Lisa Branz, Patricia Brockmann and Annika Hinze
• KanCMD: Kannada CodeMixed Dataset for Sentiment Analysis and Offensive Language Detection
  Adeep Hande, Ruba Priyadharshini and Bharathi Raja Chakravarthi
• Multilingual Emoticon Prediction of Tweets about COVID-19
  Stefanos Stoikos and Mike Izbicki
• Contextual Augmentation of Pretrained Language Models for Emotion Recognition in Conversations
  Jonggu Kim, Hyeonmok Ko, Seoha Song, Saebom Jang and Jiyeon Hong
• The LiLaH Emotion Lexicon of Croatian, Dutch and Slovene
  Nikola Ljubešić, Ilia Markov, Darja Fišer and Walter Daelemans
• Experiencers, Stimuli, or Targets: Which Semantic Roles Enable Machine Learning to Infer the Emotions?
  Laura Ana Maria Oberländer, Kevin Reich and Roman Klinger
• Topic and Emotion Development among Dutch COVID-19 Twitter Communities in the early Pandemic
  Boris Marinov, Jennifer Spenader and Tommaso Caselli
• Cross-lingual Emotion Intensity Prediction
  Irean Navas Alejo, Toni Badia and Jeremy Barnes
• Sentiments in Russian Medical Professional Discourse during the Covid-19 Pandemic
  Irina Ovchinnikova, Liana Ermakova and Diana Nurbakova
• Inferring Neuroticism of Twitter Users by Utilizing their Following Interests
  Joran Cornelisse and Raoul Grasman
• Social Media Unrest Prediction during the COVID-19 Pandemic: Neural Implicit Motive Pattern Recognition as Psychometric Signs of Severe Crises
  Dirk Johannßen and Chris Biemann
• Persuasiveness of News Editorials depending on Ideology and Personality
  Roxanne El Baff, Khalid Al Khatib, Benno Stein and Henning Wachsmuth
• Matching Theory and Data with Personal-ITY: What a Corpus of Italian YouTube Comments Reveals About Personality
  Elisa Bassignana, Malvina Nissim and Viviana Patti

Paper Submission

We invite submissions of up to nine (9) pages maximum, plus bibliography for long papers and four (4) pages, plus bibliography, for short papers. Position papers can be both long and short. For all paper types, unlimited pages for references are allowed. All papers should be electronically submitted in PDF format via the START system, available at:

https://www.softconf.com/coling2020/PEOPLES/

Submissions must be anonymous and follow the COLING 2020 style templates. The review process will be double-blind.

Programme Committee

• Jeremy Barnes, University of Oslo, Norway
• Maria Barrett, IT University of Copenhagen, Denmark
• Pierpaolo Basile, University of Bari, Italy
• Valerio Basile, University of Turin, Italy
• Meriem Beloucif, Universität Hamburg, Germany
• Laura Bostan, University of Stuttgart, Germany
• Erik Cambria, Nanyang Technological University, Singapore
• Tommaso Caselli, University of Groningen, The Netherlands
• Chloé Clavel, LTCI-CNRS, Telecom-ParisTech, France
• Walter Daelemans, University of Antwerp, Belgium
• Dipankar Das, Jadavpur University, India
• Esin Durmus, Cornell University, US
• Tommaso Fornaciari, Bocconi University, Italy
• Aparna Garimella, University of Michigan, USA
• Albert Gatt, University of Malta, Malta
• Rob van de Goot, IT University of Copenhagen, Denmark
• Mareike Hartmann, University of Copenhagen, Denmark
• Delia Irazú Hernández Farías, Universidad de Guanajuato Campus León, Mexico
• Aditya Joshi, CSIRO, AU
• Svetlana Kiritchenko, NRC-Canada, Canada
• Roman Klinger, University of Stuttgart, Germany
• Florian Kunneman, Vrije Universiteit Amsterdam, The Netherlands
• Fei Liu, Melbourne University, Australia
• Gosse Minnema, University of Groningen, The Netherlands
• Nikola Ljubešić, Jožef Stefan Institute, Slovenia
• Kim Luyckx, Antwerp University Hospital, Belgium
• Dong Nguyen, Utrecht University, The Netherlands
• Scott Nowson, Artificial Intelligence Lead, PwC Middle East, United Arab Emirates
• Debora Nozza , Bocconi University, Italy
• Endang Wahyu Pamungkas, University of Turin, Italy
• Daniel Preotiuc-Pietro, Bloomberg, USA
• Paolo Rosso, Technical University of Valencia, Spain
• Ingmar Weber, QCRI, Qatar
• Charlie Welch, University of Michigan, USA

General Chairs and Organisers

• Malvina Nissim, University of Groningen
• Viviana Patti, University of Turin
• Barbara Plank, IT University of Copenhagen

Publicity and Publication Chair

• Esin Durmus, Cornell University, US