A comprehensive classification of affective states is crucial for areas like #EmotionAI and #EmotionRecognition since it is directly connected to the acuracy with which systems recognize emotional and social behaviour. Read more in our recent pre-print at: https://t.co/wJTRQgd0ba https://t.co/CnWDMQY7D8
This is an open access article distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, reproduction and adaptation in any medium and for any purpose provided that it is properly attributed. For attribution, the original author(s), title, publication source (PeerJ Preprints) and either DOI or URL of the article must be cited.
Cite this article
Konstantinova M, Kazimirova E, Perepelkina O.2018. Classification of affective and social behaviors in public interaction for affective computing and social signal processing. PeerJ Preprints6:e26729v1https://doi.org/10.7287/peerj.preprints.26729v1
There are numerous models for affective states classification and social behavior description. Despite proving their reliability, some of these classifications turn out to be redundant, while others — insufficient for certain practical purposes. In this paper we propose a classification describing human behavior in the course of public interaction. We relied on existing literature to adopt the current achievements to a practical task---to automatically detect various aspects of human behavior. Our goal was not to suggest a new universal model describing human behavior, but to create a quite comprehensive list of affective and social behaviors in public interaction. The final list consists of the following seventeen scales: happiness, surprise, anxiety, anger, sadness, disgust, shame, pride, contempt, admiration, self-presentation, self-disclosure, mental effort, friendliness, engagement, pleasure and self-confidence. These scales concern only behavior patterns which can be observed by outside annotator and do not include personal traits or hidden states.
This paper contains the review of existing literature about affective and social behaviors models and the list of states proposed for affective computing and social signal processing