Final Call
AffCon 2020: AAAI Workshop on Measurement and Analysis of Affect
Venue: AAAI Conference, New York City, February 7th or 8th (to be finalized), 2020.
CALL FOR PAPERS
The role of affect in consumer behavior is well studied in literatures across Consumer Psychology and Marketing Science. Data have become available on self-expressions across many platforms, generating increased interest in studying affect, in settings beyond experiments. Yet, analysis of affect has lagged behind in at least two ways: (i) lack of advances in its measurement relative to access to data from which to measure affect; and (ii) significant underrepresentation of user behavior in quantitative models relative to affect's perceived importance. These are major omissions because current models use what can be measured, rather than what should be measured. When not measured, important effects get ignored, resulting in poor decision models. In turn, this leads to poorly-informed marketer actions at scale from large data, such as, predictions and recommendations. In short, although the role of affect is widely recognized, its use in computational models is stymied by weak measurement.
Computational linguists bring knowledge and tools from Natural Language Processing and Machine Learning to address these problems. The other half come from understanding of consumer behavior, where Consumer Psychologists and Marketing Scientists play crucial roles. The AffCon2020 workshop is the Third in a series at the AAAI, to bring together intellectual leadership from these two communities in a single forum to cross-pollinate research toward comprehensive analysis of affect from Big Data. Held alongside the major AI conference gives the workshop prominence and voice to promote more research in the confluence of Consumer Psychology, Marketing Science, AI, Computational Linguistics, and Human-Computer Interaction.
The theme of AffCon2020 is the study of affect in content comprising interactive response (interactive content) that may evolve over time. In this context, 'affect' refers to emotions, sentiments, moods, and attitudes including subjective evaluations, opinions, and speculations. Psychological models of affect conceptualize and measure users' opinions, intentions, motivations and expressions. Research also recognizes context-specific characteristics of human affect including how content is created as consequence of interactions among individuals with different motivations and objectives. All this suggests the need to measure affect in ways that recognize multiple interpretations of human responses found in interactive content. The Affcon2020 workshop welcomes submissions on topics including (but not limited to):
● Modeling consumer's affective reactions from Big data
● Computational models for consumer behavior theories
● Consumer psychology at scale from big data
● Inclusion of Affect in Automated Consumer Choice Models for Big data
● Measurement and evaluation of affective content
● Affective commonsense reasoning
● Affective human-agent, -computer, and-robot interaction
● Multimodal emotion recognition and sentiment analysis
● Psycho-demographic profiling
● Machine learning and Deep learning models for affect modeling in content (image, audio, and video)
We invite papers investigating multiple related themes, industry papers, and descriptions of running projects and ongoing work. In the spirit of getting a multidisciplinary community together, we also invite pre-published / in-press work as a part of a short presentation and poster session.
Workshop Format
This full-day workshop will have several prominent interdisciplinary invited speakers from the fields of linguistics, psychology, and marketing science to lead the presentation sessions. In a poster session in the afternoon, a few papers deemed more suited for a poster than a presentation will be invited to display a poster or a demo. The workshop will end with a fishbowl-style discussion among the organizers and participants to decide on future directions for the workshop and the research community.
Workshop URL: https://sites.google.com/view/affcon2020
Workshop Submission Site - EasyChair Link - https://easychair.org/conferences/?conf=affcon2020
AAAI 2020 Conference link: https://aaai.org/Conferences/AAAI-20/
AAAI 2020 Workshop list: https://aaai.org/Conferences/AAAI-20/ws20/ (W1: Affective Content Analysis (AffCon 2020): Interactive Affective Response)
Shared Task
To encourage development of computational models, the workshop offers an opportunity for a shared task, CL-Aff, on a provided dataset. There is a growing interest in understanding how humans initiate and hold conversations. The affective understanding of conversations focuses on the problem of how speakers use affect to react to a situation and to each other. We introduce the OffMyChest Conversation dataset, and invite submissions for the Computational Linguistics Affect Understanding (CL-Aff) Shared Task on Affect in Conversations.
Submissions
Submissions should be made via EasyChair and must follow the formatting guidelines for AAAI-2020 (use the AAAI Author Kit). All submissions must be anonymous and conform to AAAI standards for double-blind review. Both full papers (8 page long including references) and short papers (4 page long including references) that adhere to the 2-column AAAI format will be considered for review.
Co-chairs:
Niyati Chhaya, Primary Contact (Adobe Research, nchhaya@adobe.com),
Kokil Jaidka (Nanyang Technological University, kokil.j@gmail.com ),
Jennifer Healey (Adobe Research, jehealey@adobe.com),
Lyle Ungar (University of Pennsylvania, ungar@cis.upenn.edu),
Atanu R Sinha (Adobe Research, atr@adobe.com)
IMPORTANT Dates
November 7, 2019: Abstract Submission (optional) , Submissions via EasyChair
November 15, 2019: Full paper submission
December 04, 2019: Notification of Acceptance/ Rejection
December 13, 2019: AAAI-20 Early registration deadline
December 15, 2019: Camera-ready Versions due
February 7/8 , 2020: Workshop at AAAI-20
CL-Aff Shared Task Submission Deadlines
Submissions via EasyChair (prefix your submission title with "[CL-Aff Shared Task]")
September 15, 2019 - Unlabeled dataset, instructions and label descriptions released
September 18, 2019 - Training set released
October 15, 2019 - Abstract submission with a short system description
October 30, 2019 - Test set released
November 30, 2019 - System runs due & AAAI conference early registration deadline
December 15, 2019 - System reports (full papers) due and peer review process begins
January 17, 2020- Camera-ready contributions
__________________
END OF ANNOUNCEMENT