<p>The Affective PDF Reader is a PDF Reader combined with affect recognition systems. The aim of the project is to research a way to provide the reader of a PDF with real - time visual feedback while reading the text to influence the reading experience in a positive way. The visual feedback is given in accordance to analyzed emotional states of the person reading the text - this is done by capturing and interpreting affective information with a facial expression recognition system. Further enhancements would also include analysis of voice in the computation as well as gaze tracking software to be able to use the point of gaze when rendering the visualizations.The idea of the Affective PDF Reader mainly arose in admitting that the way we read text on computers, mostly with frozen and dozed off faces, is somehow an unsatisfactory state or moreover a lonesome process and a poor communication. This work is also inspired by the significant progress and efforts in recognizing emotional states from video and audio signals and the new possibilities that arise from.The prototype system was providing visualizations of footprints in different shapes and colours which were controlled by captured facial expressions to enrich the textual content with affective information. The experience showed that visual feedback controlled by utterances of facial expressions can bring another dimension to the reading experience if the visual feedback is done in a frugal and non intrusive way and it showed that the evolvement of the users can be enhanced.</p>

The Affective PDF Reader is a PDF Reader combined with affect recognition systems. The aim of the project is to research a way to provide the reader of a PDF with real - time visual feedback while reading the text to influence the reading experience in a positive way. The visual feedback is given in accordance to analyzed emotional states of the person reading the text - this is done by capturing and interpreting affective information with a facial expression recognition system. Further enhancements would also include analysis of voice in the computation as well as gaze tracking software to be able to use the point of gaze when rendering the visualizations.The idea of the Affective PDF Reader mainly arose in admitting that the way we read text on computers, mostly with frozen and dozed off faces, is somehow an unsatisfactory state or moreover a lonesome process and a poor communication. This work is also inspired by the significant progress and efforts in recognizing emotional states from video and audio signals and the new possibilities that arise from.The prototype system was providing visualizations of footprints in different shapes and colours which were controlled by captured facial expressions to enrich the textual content with affective information. The experience showed that visual feedback controlled by utterances of facial expressions can bring another dimension to the reading experience if the visual feedback is done in a frugal and non intrusive way and it showed that the evolvement of the users can be enhanced.

Background: Risky security behaviour displayed by end-users has the potential to leave devices vulnerable to compromise, despite the availability of security tools designed to aid users in defending themselves against potential online threats. This indicates a need to modify the behaviour of end-users, allowing them to consider the security implications of their actions online. Previous research has indicated affective feedback may serve as a successful method of educating users about risky security behaviours. Thus, by influencing end-users via affective feedback it may be possible to engage users, improving their security awareness. Aims: Develop and apply knowledge of monitoring techniques and affective feedback, establishing if this changes users’ awareness of risky security behaviour in the context of a browser-based environment. Methodology: The methodology employs the use of log files derived from the monitoring solution, and information provided by users during the experiments. Questionnaire data was compared against log files and information provided during experiments, providing an overall quantitative approach. Results: In the case of the log files and questionnaires, participants were found to have engaged in instances of risky security behaviours, which they were unaware of, and this indicated a low-level of awareness of risky security behaviour. Whilst the results indicate the affective feedback did not make a difference to behaviour during the course of the experiments, participants felt that the affective feedback delivered had an impact, raising their security awareness, encouraging them to learn about online security. Conclusions: This body of research has made a novel contribution to the field of affective feedback and usable security. Whilst the results indicate the affective feedback made no difference to behaviour, users felt it had an impact on them, persuading them to consider their security behaviours online, and encouraging them to increase their knowledge of risky security behaviours. The research highlights the potential application of affective feedback in the field of usable security. Future work seeks to explore different ways in which affective feedback can be positioned on-screen, and how feedback can be tailored to target specific groups, such as children, or elderly people, with the aim of raising security awareness.

Human-Computer Interaction migrates from the classic perspective to a more natural environment, where humans are able to use natural language to exchange knowledge with a computer. In order to fully "understand" the human's intentions, the computer should be able to detect emotions and reply accordingly. This thesis focuses on several issues regarding the human affects, from various detection techniques to their integration into a Distributed Interactive System. Emotions are a fuzzy concept and their perception across human individuals may vary as well. Therefore, this makes the detection problem very difficult for a computer. From the affect detection perspective, we proposed three different approaches: an emotion detection method based on Self Organizing Maps, a valence classifier based on multi-modal features and Support Vector Machines, and a technique to resolve conflicts into a well known affective dictionary (SentiWordNet). Moreover, from the system integration perspective, two issues are approached: a Wizard of Oz experiment in a children storytelling environment and an architecture for a Distributed Interactive System.

L’Interaction Humain-Machine a évolué d’une perspective classique vers un environnement plus naturel, dans lequel les humains peuvent utiliser la langue naturelle pour échanger des connaissances avec un ordinateur. Pour bien “comprendre” les intentions de l’humain, l’ordinateur doit être capable de détecter les émotions et de répondre en conséquence. Cette thèse porte sur plusieurs aspects de la détection des émotion humaines, en partant de différentes techniques de détection jusqu’à leur intégration dans un Système Interactif Distribué. Les émotions sont un concept flou et leur perception par des individus humains peut aussi varier. Par conséquent, cela rend le problème de détection très difficile en informatique. Du point vue de la détection de l’affect, nous avons proposé trois approches différentes : une méthode à base de Cartes Auto-Organisatrices (Self Organizing Maps- SOM), un classifieur de la valence basé sur des caractéristiques multi-modales et un Séparateur à Vaste Marge (Support Vector Machines - SVM) et une technique pour résoudre les conflits dans un dictionnaire affectif (SentiWordNet). En outre, du point de vue de l’intégration aux systèmes, deux questions sont abordées : une expérience de type Magicien d’Oz dans un environnement de narration d’histoires pour enfants et une architecture de Système Interactif Distribué. / Human-Computer Interaction migrates from the classic perspective to a more natural environment, where humans are able to use natural language to exchange knowledge with a computer. In order to fully “understand” the human’s intentions, the computer should be able to detect emotions and reply accordingly. This thesis focuses on several issues regarding the human affects, from various detection techniques to their integration into a Distributed Interactive System. Emotions are a fuzzy concept and their perception across human individuals may vary as well. Therefore, this makes the detection problem very difficult for a computer. From the affect detection perspective, we proposed three different approaches: an emotion detection method based on Self Organizing Maps, a valence classifier based on multi-modal features and Support Vector Machines, and a technique to resolve conflicts into a well known affective dictionary (SentiWordNet). Moreover, from the system integration perspective, two issues are approached: a Wizard of Oz experiment in a children storytelling environment and an architecture for a Distributed Interactive System.