Interaction mediated through the Internet is changing the ways in which people connect, communicate, and share information and emotions. At the same time, this enables studies of these processes hitherto impossible by acquiring large, content-rich, highly interconnected data-sets that enable both quantitative and qualitative analysis on an unprecedented scale. The ongoing evolution of Internet services and of the ways in which we use them in daily life influences not only our interaction patterns but also our susceptibility to the communicated content, including our emotional responses.

In this paper, we cover how interactive affective systems can be used to study the genesis and the influence of collective emotions in online communication, progressing from one-on-one scenarios to ones that entail modelling of more complex, multi-agent communication processes. The presented approach is supplementary to automatic sentiment classification and data-mining of users’ posts in online social media. The introduction of affective dialog systems as interactive tools enables to extend the scope of analysis both qualitatively, i.e., by engaging users in follow-up dialogs, and quantitatively, i.e., by reaching the usually silent majority: users who normally refrain from voicing their opinion in asynchronous online channels. In this paper we also give an overview of useful methods for affect detection and user modelling in the context of affective dialog management. Further, we present experimental settings for our interactive affective systems and corresponding results. We conclude by discussing the relation between the acquired insights and a general framework for modelling the role of collective emotions in ICT-mediated communication channels.

• Legal notice:
  

  Copyright (c) Pielaszek Research, all rights reserved.
  The above materials, including auxiliary resources, are subject to Publisher's copyright and the Author(s) intellectual rights. Without limiting Author(s) rights under respective Copyright Transfer Agreement, no part of the above documents may be reproduced without the express written permission of Pielaszek Research, the Publisher. Express permission from the Author(s) is required to use the above materials for academic purposes, such as lectures or scientific presentations.
  In every case, proper references including Author(s) name(s) and URL of this webpage: https://science24.com/paper/28451 must be provided.

1. Patterns of Online Chats with Emotional Bots: Data Analysis and Agent-Based Simulations
2. Entropy-growth-based model of emotionally charged online dialogues