Catálogo de publicaciones - libros

RoCo, a novel robotic computer, has the capability to move its monitor in subtly expressive ways that respond to and promote its user’s postural movement. Motivated by Riskind’s “Stoop to conquer” research where it was found that postures congruous to the type of outcome a person received (e.g. slumping following a failure or sitting up proudly following a success) led to significantly better performance in a subsequent cognitive task than incongruous postures (e.g. sitting up proudly following a failure or slumping following success), we performed two experiments where RoCo was used to manipulate its user’s posture. Our results show that people tend to be more persistent on a subsequent task when RoCo’s posture is congruous to their affective state than when it is incongruous. Our study is the first to show that a computer’s “pose,” congruous or incongruous to a user’s affective state, can influence factors such as persistence in problem solving tasks.

A video affective content representation and recognition framework based on Video Affective Tree (VAT) and Hidden Markov Models (HMMs) is presented. Video affective content units in different granularities are firstly located by excitement intensity curves, and then the selected affective content units are used to construct VAT. According to the excitement intensity curve the affective intensity of each affective content unit at different levels of VAT can also be quantified into several levels from weak to strong. Many middle-level audio and visual affective features, which represent emotional characteristics, are designed and extracted to construct observation vectors. Based on these observation vector sequences HMMs-based video affective content recognizers are trained and tested to recognize the basic emotional events of audience (joy, anger, sadness and fear). The experimental results show that the proposed framework is not only suitable for a broad range of video affective understanding applications, but also capable of representing affective semantics in different granularities.

According to traditional animators, the art of building believable characters resides in the ability to successfully portray a character’s behaviour as the result of its internal emotions, intentions and thoughts. Following this direction, we want our agents to be able to explicitly talk about their internal thoughts and report their personal past experiences. In order to achieve it, we look at a specific type of episodic long term memory. This paper describes the integration of Autobiographic Memory into FAtiMA, an emotional agent architecture that generates emotions from a subjective appraisal of events.

A study is reported that examined the effectiveness of computerbased image retrieval as a support tool for creative industrial design. Participants were given a design brief for a concept car, and asked to retrieve images from the web that would provide inspiration for this design task. They then rated various aesthetic, affective, and inspirational aspects of the images, and a second sample of participants rated the search terms that they had used. Emotional inspiration was important to designers, arising in part from a broad semantic theme and in part from the inspirational values of the more ’fundamental’ image properties of colour and layout. The pattern of results suggested that some designers adopted a more risky (less efficient) search strategy in order to access emotional image content. Aesthetic and affective aspects of the retrieved images predicted inspirational value.

In this paper, we describe the integration of Natural Language Processing (NLP) within an emotional planner to support Interactive Storytelling. Our emotional planner is based on a standard HSP planner, whose originality is drawn from altering the agents’ beliefs and emotional states. Each character is driven by its own planner, while characters are able to operate on their reciprocal feelings thus affecting each other. Our baseline story is constituted by a classic XIX century French novel from Gustave Flaubert in which characters feelings play a dominant role. This approach benefits from the fact that Flaubert has described a specific ontology for his characters feelings. The objective of NLP should be to uncover from natural language utterances the same kind of affective elements, which requires an integration between NLP and the planning component at the level of semantic content. This research is illustrated with examples from a first fully integrated prototype comprising NLP, emotional planning and real-time 3D animation.

Using synthetic characters to support children’s personal, social and emotional education requires that the emotional response elicited from the children is that desired by educators and stakeholders. This paper discusses an approach to understanding children’s emotional interpretation of character’s behaviour in a complex social situation. We outline this approach based on Theory of Mind concepts, that we have developed to enable us to understand and analyse children’s emotional interpretation of synthetic characters involved in bullying scenarios in a virtual school. We discuss an empirical study of 345 children, aged 8-11 years, and concluded that our approach enabled us to gain a greater understanding of children’s emotional interpretations. Results from the study identified that overall children did make appropriate emotional interpretations of characters and story, highlighting the potential of synthetic characters for exploring personal, social and emotional issues.

It has been shown that users of a digital system perceive a more ’masculine-sounding’ female voice as more persuasive and intelligent than a corresponding but more ’feminine-sounding’ female voice. Our study explores whether a parallel pattern of affectively colored evaluations can be elicited when and are manipulated via cues instead of via voice. 80 participants encountered synthetic characters, visually manipulated in terms of femininity and masculinity but with voice, spoken content, linguistic style and role of characters held constant. Evaluations of the two female characters differed in accordance with stereotype predictions - with the exception of competence-related traits; for the two male characters evaluations differed very little. The pattern for versus characters was slightly in opposite to stereotype predictions. Possible explanations for these results are proposed. In conclusion we discuss the value of being aware of how different traits in synthetic characters may interact.

We analyze the antecedents of affective states in a simulation problem-solving environment, The Incredible Machine: Even More Contraptions, through quantitative field observations of high school students in the Philippines using that system. We investigate the transitions between affective states over time, finding that several affective states, including flow, boredom, and frustration, but not surprise, tend to persist over for relatively long periods of time. We also investigate how students’ usage choices influence their later affect, finding that gaming the system leads to reduced confusion but increased boredom.

We use a analysis on our spoken dialogue tutoring corpus to investigate dependencies between uncertain student answers and 9 dialogue acts the human tutor uses in his response to these answers. Our results show significant dependencies between the tutor’s use of some dialogue acts and the uncertainty expressed in the prior student answer, even after factoring out the answer’s (in)correctness. Identification and analysis of these dependencies is part of our empirical approach to developing an adaptive version of our spoken dialogue tutoring system that responds to student affective states as well as to student correctness.

Recently, a new fundamental discovery has been made of the relationship between attentional system and affective system of human brain, giving rise to the devaluation-by-inhibition hypothesis. It is shown that selective attention has an affective impact on an otherwise emotionally bland stimulus. Particularly, if a neutral stimulus was inhibited by selective attention in a prior task, it would be valued less in a subsequent affective evaluation task than it would otherwise have been. In the present study, we extend this line of research on the affective consequence of attention and demonstrate that prior attentional states (attended or inhibited) associated with a group of neutral stimuli (character strings) can even influence subsequent preference judgment about previously-unseen stimuli if these new stimuli share certain basic features (e.g., follow the same rule) with those encountered in a previous stage.