Affective Multisensorial Books

Abstract

Affective computing devices have been used in e-learning, game, and movie areas to acquire individuals' affective states. Thus, states like fun, boredom, frustration, and excitement can be detected. Based on these states, many tasks can be executed. For example, if an individual practicing an exercise in an e-learning system is bored, some action can be executed by the system; for example, it could present more challenging tasks. Inspired by the above scenario, the present work proposes the creation of a model based on e-books reading, multisensorial media (MulSeMedia) area, and affective computing area. This model is referred to as Affective Multisensorial Books, and it has two main goals: (i) acquire affective states from users; (ii) produce multisensorial media effects. The main motivation is related to the fact that MulSeMedia can improve Quality of Experience of individuals and affective computing can be used to capture individuals' affective states during reading (e.g., boredom). However, it is important to evaluate if it is possible to detect changes in affective states of individuals in the reading task. In this scenario, this work evaluates if there are statistical differences in the same individual reading two genres of texts. The first one is a drinking fountain guide page, and the second is a poem. The Wilcoxon signed-rank test was used to assess the difference in mean of measurements in Galvanic Skin Response of individuals when reading each of the texts. The analysis indicates a statistically significant difference between the reading of the two texts.