Marcin Skowron

Emotional persistence in online chatting communities

How do users behave in online chatrooms, where they instantaneously read and write posts? We analyzed about 2.5 million posts covering various topics in Internet relay channels, and found that user activity patterns follow known power-law and stretched exponential distributions, indicating that online chat activity is not different from other forms of communication. Analysing the emotional expressions (positive, negative, neutral) of users, we revealed a remarkable persistence both for individual users and channels. I.e. despite their anonymity, users tend to follow social norms in repeated interactions in online chats, which results in a specific emotional “tone” of the channels. We provide an agent-based model of emotional interaction, which recovers qualitatively both the activity patterns in chatrooms and the emotional persistence of users and channels. While our assumptions about agents emotional expressions are rooted in psychology, the model allows to test different hypothesis regarding their emotional impact in online communication.

Damping sentiment analysis in online communication: discussions, monologs and dialogs

Sentiment analysis programs are now sometimes used to detect patterns of sentiment use over time in online communication and to help automated systems interact better with users. Nevertheless, it seems that no previous published study has assessed whether the position of individual texts within on-going communication can be exploited to help detect their sentiments. This article assesses apparent sentiment anomalies in on-going communication --- texts assigned significantly different sentiment strength to the average of previous texts --- to see whether their classification can be improved. The results suggest that a damping procedure to reduce sudden large changes in sentiment can improve classification accuracy but that the optimal procedure will depend on the type of texts processed.

Structure and stability of online chat networks built on emotion-carrying links

High-resolution data of online chats are studied as a physical system in the laboratory in order to quantify collective behavior of users. Our analysis reveals strong regularities characteristic of natural systems with additional features. In particular, we find self-organized dynamics with long-range correlations in user actions and persistent associations among users that have the properties of a social network. Furthermore, the evolution of the graph and its architecture with specific k-core structure are shown to be related with the type and the emotion arousal of exchanged messages. Partitioning of the graph by deletion of the links which carry high arousal messages exhibits critical fluctuations at the percolation threshold.

An interdisciplinary VR-architecture for 3D chatting with non-verbal communication

The communication between avatar and agent has already been treated from different but specialized perspectives. In contrast, this paper gives a balanced view of every key architectural aspect: from text analysis to computer graphics, the chatting system and the emotional model. Non-verbal communication, such as facial expression, gaze, or head orientation is crucial to simulate realistic behavior, but is still an aspect neglected in the simulation of virtual societies. In response, this paper aims to present the necessary modularity to allow virtual humans (VH) conversation with consistent facial expression -either between two users through their avatars, between an avatar and an agent, or even between an avatar and a Wizard of Oz. We believe such an approach is particularly suitable for the design and implementation of applications involving VHs interaction in virtual worlds. To this end, three key features are needed to design and implement this system entitled 3D-emoChatting. First, a global architecture that combines components from several research fields. Second, a real-time analysis and management of emotions that allows interactive dialogues with non-verbal communication. Third, a model of a virtual emotional mind called emoMind that allows to simulate individual emotional characteristics. To conclude the paper, we briefly present the basic description of a user-test which is beyond the scope of the present paper.

Applying a Text-Based Affective Dialogue System in Psychological Research: Case Studies on the Effects of System Behaviour, Interaction Context and Social Exclusion

This article presents two studies conducted with an affective dialogue system in which text-based system–user communication was used to model, generate and present different affective and social interaction scenarios. We specifically investigated the influence of interaction context and roles assigned to the system and the participants, as well as the impact of pre-structured social interaction patterns that were modelled to mimic aspects of “social exclusion” scenarios. The results of the first study demonstrate that both the social context of the interaction and the roles assigned to the system influence the system evaluation, interaction patterns, textual expressions of affective states, as well as emotional self-reports. The results observed for the second study show the system’s ability to partially exclude a participant from a triadic conversation without triggering significantly different affective reactions or a more negative system evaluation. The experimental evidence provides insights on the perception, modelling and generation of affective and social cues in artificial systems that can be realized in different modalities, including the text modality, thus delivering valuable input for applying affective dialogue systems as tools for studying affect and social aspects in online communication.

ENTROPY-GROWTH-BASED MODEL OF EMOTIONALLY CHARGED ONLINE DIALOGUES

We analyze emotionally annotated massive data from Internet relay chat (IRC) as well as from BBC forum website and model the dialogues between chat participants by assuming that the driving force for the discussion is the entropy growth of emotional probability distribution. This process is claimed to be responsible for a power-law distribution of the discussion lengths observed in the dialogues. We perform numerical simulations based on the noticed phenomenon obtaining a good agreement with the real data. Finally, we propose a method to artificially prolong the duration of the discussion that relies on the entropy of emotional probability distribution.

Predicting Genre Preferences from Cultural and Socio-Economic Factors for Music Retrieval

In absence of individual user information, knowledge about larger user groups (e.g., country characteristics) can be exploited for deriving user preferences in order to provide recommendations to users. In this short paper, we study how to mitigate the cold-start problem on a country level for music retrieval. Specifically, we investigate a large-scale dataset on user listening behavior and show that we can reduce the error for predicting the popularity of genres in a country by about 16.4% over a baseline model using cultural and socio-economics indicators.

Collective Emotions Online

This chapter analyzes patterns in messages posted to several Internet discussion forums from the perspective of the sentiment expressed in them and the collective character of observed emotions. A large set of records describing comments expressed in diverse cyber communities—blogs, forums, IRC channels, and the Digg community—was collected, and sentiment classifiers were used to estimate the emotional valence (positive, negative, or neutral) of each message. A comparison with simple models showed that the data included clusters of comments with the same emotional valence that were much longer than similar clusters created by a random process. This shows that there are emotional interactions between participants so that future posts tend to have the same valence as previous posts. Threads starting from a larger number of negative comments also last longer so negative emotions can be treated as a kind of discussion fuel; when the fuel (negativity) is used up in the discussion, it may finish. Moreover, the amount of user activity in a particular thread correlates positively with the presence of negative emotions expressed by the individual user in the thread. In summary, the analyses describe individual and collective patterns of emotional activities of Web forum users and suggest that negativity is needed to fuel important discussions.

Adaptive Mind Agent

We present the Adaptive Mind Agent, an intelligent virtual agent that is able to actively participate in a real-time, dynamic environment. The agent is equipped with a collection of processing tools that form the basis of its perception from and action on the environment consisting of web documents, URLs, RRS feeds, domain-specific knowledgebases, other accessible virtual agents and the user. How these predispositions are finally shaped into unique agent behaviour depends on the agents abilities to learn through actual interactions, in particular the abilities: (i) to memorize and evaluate episodes comprising the actions the agent had performed on its environment in the past depending on its perceptions of the user requests and its interpretation of the users feedback reinforcing or inhibiting a certain action; (ii) to dynamically develop user-driven interest and preference profiles through memorizing and evaluating the user clicks on selected web pages.

Entropy growth in emotional online dialogues

We analyze emotionally annotated massive data from IRC (Internet Relay Chat) and model the dialogues between its participants by assuming that the driving force for the discussion is the entropy growth of emotional probability distribution.