About the Workshop

AffCon-2021 is the fourth Affective Content Analysis workshop @ AAAI. The workshop series (i) builds upon the state of the art in neural and AI methods, for modeling affect in interpersonal interactions and behaviors and (ii) brings a confluence of research viewpoints representing several disciplines.

The 2021 edition of the workshop takes interaction in yet another new direction. A large share of content created are outcomes of collaboration. Among others, a basic question worth examining is whether and how collaboration among creatives impact the affective characteristics of the content. A follow up question then is how to model and computationally measure affect in collaborative creation. These are difficult questions especially because the process of exchanges among collaborators is opaque, only the outcome is transparent. .

This year, collaboration takes on an extra meaning in a physically distanced world, with reliance even more heavily on computer-mediated cooperation. Understanding the dynamics of affect in collaborative content is more topical. The theme for AffCon@AAAI-2021 is ‘Affect in Collaborative Creation’. The theme is relevant for increasingly decentralized workplaces, asynchronous collaborations, and computer-mediated communication. Studying and codifying user reactions in this setup can help understand the society and aid towards better tools for content analysis. The computer mediated collaboration may also produce data to examine these phenomena.

Once again we're announcing a Shared Task to encourage the development of new models and approaches for affect in interactions.

The subjective nature of human affect suggests the need to measure in ways that recognize multiple interpretations of human responses. A few key challenges are:

• Standardizing the measurement of affect in order to meaningfully compare different affective models against each other

• Addressing the challenges in cross-media, cross-domain and cross-platform affect analysis

• Identifying consumer psychology theories and behaviors related to affect, which are amenable to computational modeling

The AI community is well-poised to propose new solutions, approaches and frameworks to tackle these and other challenges. This workshop invites papers that address these and other topics, propose novel solutions for well-established problems, offer modeling and measurement of affect, and identify the best affect–related dimensions to study consumer behavior. Potential examples include deep learning for affect analysis, leveraging traditional affective computing algorithms (that are built on multi–modal data and sensors) for text and so on.

Another area of focus for this workshop is the need of standardized baselines, datasets, and evaluation metrics. Papers describing novel language resources, evaluation metrics and standards for affect analysis and understanding are also encouraged.