This capstone project presents the development of a framework for selecting mobile sensors for the digital phenotyping of university students with possible depressive profiles. Inspired by a seminal study by Torous that analyzes digital phenotyping in varied contexts, this work performs a critical reinterpretation of this literature to adapt and apply concepts to the specific context of depression in academic settings. The proposed framework was developed based on a review of existing work that uses behavioral data captured by sensors on smartphones and other mobile devices, such as GPS and accelerometers, to identify patterns that may be related to depressive symptoms. The methodology involved collaborative discussions with experts in computing and health, seeking to align the technical capabilities of the sensors with the diagnostic and therapeutic needs of potentially depressed students. As a result, possible relationships are presented between the data collected by the sensors and symptoms of depression. This study aims to provide a basis for future practical implementations of computer systems mental health support, using accessible and non-intrusive technologies in educational contexts.

The model considers mobile sensors and Online Social Networks (RSO) data. The outputs of the classification model influence the delivery of interventions designed within the scope of the Amive project. Based on the classification, a chatbot starts conversations about determinants of mental suffering in the university context, offering health education content and pointing out support techniques and places. Therefore, these conversations must be carried out welcoming and intuitive. With this in mind, this undergraduate final work aims to explore successful chatbot solutions, to extract design elements to add to the Amive project proposal. To this end, a Benchmark was carried out with eight systems comparing aspects that included communication format, demonstration of user reaction to messages, and graphic representation (avatar). As a result, five suggestions for improvements to the design solution were listed and applied in a redesign process that generated a medium-fidelity prototype.

higher than in the general population. This work proposes a computing infrastructure that uses digital phenotyping data collected by mobile and wearable sensors, such as smartphones and smartwatches, to identify Brazilian university students with a possible depressive profile (PPD). Adopting the Design Science Research (DSR) methodology, the study develops a computational solution whose effectiveness is validated through a descriptive exploratory analysis of the collected data. This approach seeks not only to validate the feasibility of the proposed infrastructure but also to facilitate the identification of behavioral patterns associated with the PPD. The approach includes the use of the "Human in the Loop" method for removing data outliers and employs the t-SNE (t-distributed Stochastic Neighbor Embedding) technique for reducing high-dimensional data and identifying patterns in interpreting the results. This work aligns with the principles of Human-Computer Interaction (HCI) intending to contribute to the areas of mental health and computing.

Concerns related to mental health have been spread worldwide and computing has demanded efforts in the development of solutions to support therapies for mental disorders. Substance Use Disorders (SUDs) are no longer being treated as an individual health issue, but are also related to public and social health. Patients in recovery from SUDs are end users of therapy support systems and their involvement in the process of creating these computer systems has the potential to increase patients' autonomy and help with adherence to therapy. Studies involving the participation of end users in the construction of therapeutic systems were identified in the literature, however, in these studies, health professionals and patients participate more as information providers. Little is known about this population actively participating in the design of therapeutic solutions, more specifically, digital games with therapeutic potential. Considering this context, the motivation for this doctoral research arose from the intention to formalize a framework that could scale the design and development of digital games with therapeutic potential by people recovering from SUDs. The hypothesis was that delivering a specific design process for this population would increase the autonomy and empowerment of end users (health professionals and patients). Given the motivation to support the design and development of digital games with therapeutic potential for people recovering from SUDs, the objective of this doctoral research was to build a framework that corroborates the design and development activities by this population, providing more autonomy to those end users. In order to achieve this objective, the methodological path included, first, a Systematic Mapping (SM) carried out on computing in support of the therapy of mental disorders. In parallel, a case study was carried out with people recovering from SUDs at a Psychosocial Care Center - Alcohol and Drugs (CAPS-AD). Based on the results of the SM and the case study, it became possible to identify demands for the construction of the framework. To build the framework, the following were defined: i) a design process; ii) a set of rules for creating Conversational Agents (CAs) that can guide the end user in the design process; and iii) a web platform with an embedded CA to support the design process. After completing the development of the framework, a second case study was carried out, at CAPS-AD in another city, to evaluate the framework. The results suggest that the use of the proposed framework aroused more interest, engagement, autonomy, and empowerment of end users in the design of digital games with therapeutic potential. The main contributions of this doctoral thesis are i) State-of-the-art study on computing to support the therapy of mental disorders; ii) Lessons learned from applying a design process by people in recovery from SUDs in a real-life setting; iii) Construction of a framework for the design of digital games with therapeutic potential by people in recovery from SUDs; and iv) Evaluation of the framework with end users in recovery from SUDs.

The field of Human-Computer Interaction aims at developing computational systems that place the user at the center of the their development, so he/she can have the best experience when interact with the final solution. When it was acknowledged that emotions affect the relation of the individual with what surrounds him/her, scholars began to measure these emotions based on instruments that had been developed over the years. It should be emphasized that emotions can be seen as a composition of five components – physiological reactions, subjective feeling, motor expression, cognitive appraisals and behavioural tendencies. It is believed, therefore, that evaluating more than one component could bring results with greater correctness. Although some studies already measure the user’s emotional state to promote the adaptation of user interfaces and promote a better interaction experience, few worry about leading the user to achieve a desired emotional state. This work presents a new version of UIFlex (PROENÇA; NERIS, 2017), UIFlex 2.0. The previous version is presented as a Google Chrome plugin and it is responsible for providing interface adaptations to improve the accessibility of web pages. To do so, authors created rules of adaptation in JSON (JavaScript Object Notation) format that “injected” code into the web pages. The new proposed version brings together two major changes: (1) the architecture of the solution, which is now based on the MAPE-K model (Monitor-Analyse-Plan-Execute over a shared Knowledge) (KEPHART et al., 2003); (2) new user interface adaptation rules in order to provide color change in it according to theoretical studies published previously. Finally, a double blind experiment was conducted with 44 users in which two tasks were proposed – reading and transcript – on pages with the plugin enabled. Participants of the control group had access to UIFlex 2.0 as participants of the placebo group used UIFlex 3.0, which did not perform any adaptation. Both groups had the majority of participants reaching the desired emotional state – as can be seen in the generated incidence graphs. In addition, the Chi-Square statistical test was applied, which denied the alternative hypothesis. Thus, it is suggested that new rules be developed so that there are a greater number of changes to interface elements.

• This study collected answers by a questionnaire from 160 college Brazilian students regarding socio-demographic data, technology use, privacy and use of digital data, factors that affect mental health, strategies to preserve mental health, and 3 scenarios of computer-based technology to be judged according to the utility of technology, willingness to use it and ethics. The results indicate some different perceptions among participants considering their age, genders and areas of study, and also between the utility of technology and willingness to use it.  

As emoções são um importante aspecto da experiência que o usuário tem ao usar um sistema. Na literatura, há trabalhos que propõem sistemas que alteram as interfaces de usuário (IU) considerando emoções, levando em conta o que é sentido antes ou durante o uso. No entanto, não foram encontrados trabalhos que alteram as IU levando em consideração o estado emocional que o usuário gostaria de sentir. Além disso, como as emoções são facilmente alteradas por eventos internos e externos, é necessário oferecer IU que considerem e reajam às emoções em tempo de interação, demandando uma solução de software flexível. Também, a mensuração do estado emocional pode considerar, além da auto expressão do usuário (sentimento subjetivo), as expressões motoras, como movimentos faciais, e sinais fisiológicos, como a frequência cardíaca. A obtenção desses dados requer a adoção de diferentes sensores em contextos de uso diferenciados, o que demanda que o sistema computacional tenha alta manutenibilidade. Assim, este trabalho de conclusão de curso teve como objetivo a extensão do plugin UIFlex visando a criação de uma infraestrutura flexível, com boa manutenibilidade e que fosse capaz de oferecer, em tempo de interação, adaptações de IU pautadas nos estados emocionais que um usuário sente e deseja sentir. Além disso, foi realizada uma adequação da solução de software à blueprint MAPE-K da IBM. As versões com e sem MAPE-K foram comparadas segundo as métricas de avaliação de software. Os resultados da comparação sugerem que a adequação à blueprint trouxe benefícios para a manutenibilidade da solução proposta.

that is, 4 to 5 years in Brazil. What is clear is that, although children are exposed to computational solutions, preschool teachers are still discouraged from teaching content related to computers and technology for children, as they consider complex and unrelated to basic curricula and also due to the lack of plans that serve as pedagogical support for the application of activities in the classroom. Thus, in order to help overcome these barriers, the objective of this research is to propose and evaluate a set of activities that offer methodological didactic support so that preschool teachers can work independently on the elementary and preliminary concepts related to the knowledge of computing for children aged 4 to 5 years. To this end, the methodological approach of this research was divided into two stages: (1) used the focus group method with 6 professionals in computing and education to develop 14 lesson plans of didactic activities that addressed content related to data storage and processing, the 4 competencies of computational thinking, the approach to teaching unplugged (without the use of technologies) and, finally, linked to the axes and competencies of the Common National Curricular Base. (2) used the survey method with 113 professionals linked to preschoolers and pedagogy students to evaluate the lesson plans of the didactic activities proposed by this research using the online questionnaire technique. According to the data analysis, considering the total of 339 evaluations received from the lesson plans for each aspect of the rubric used and adapted for this research, obtained an average positive result greater than 90%. Furthermore, considering the comments to the open and non-mandatory question and the interest of the evaluators (96.5%) in applying the activities developed in the classroom after a post-pandemic scenario, the results suggest that the hypothesis of this research was confirmed and the objective achieved. However, future studies will be able to investigate how teachers autonomously apply these activities in the classroom and see if in fact children can, from practice, have a better understanding of the world with the technology around them and take ownership of new technological solutions and become possible active users. As a computer research, this project is part of the Computer Education area.

However, intended audiences are still restricted (normally to anglophone youngsters without physical, cognitive, and emotional disabilities). To overcome barriers, it is necessary to allow people with different interaction abilities and needs to contribute on game development. This thesis presents an end-user development framework for tailorable games, with the purpose of promoting inclusive creation of inclusive games. Our lemma is games for everyone, by everyone. The thesis starts from the hypothesis that if end-users used creation tools suitable to their interaction needs and followed a collaborative work model to iteratively improve accessibility features to be inserted into a software architecture able to modify human-computer interaction at use-time, then they would be able create games satisfying heterogeneous interaction needs of possible players. In this thesis, we have explored documental research (systematic review to identify current approaches), creation and specification (for required software systems, models, and architectures), and field research (to understand interaction requirements and evaluate the framework). The framework encompasses a formal software architecture for implementing inclusive games, a collaborative work model for co-creation of inclusion, and an end-user game development platform (Lepi). Our framework was used by an audience not yet considered by the Literature (adult people -- some of which with low literacy and that had never used a computer before -- undergoing supervision for alcohol and drug abuse rehabilitation) over four months. Our results show that the participants were able to create games that satisfied their own interaction needs, as well as those from people with different needs than theirs (therefore, they have confirmed our research hypothesis). We have also observed that game creation and play transformed the participants. The benefits went beyond software co-creation, towards self-improvements. In this way, we have contributed with participatory and universal to creation and access of knowledge by the Brazilian citizen. Moreover, as the architecture allows continuous inclusion of new audiences via the addition of new alternatives of use, we hope that we can continue enabling more people to create and play -- small steps from users, giant leaps towards universal access.

classified into two models of taxonomy: Discrete Model that include basic emotions(happiness, sadness, fear, disgust, anger, surprise) and Dimensional Model that expresses two or more emotions in a space, with emotional domains such as Valencia (disgust, pleasure) and Excitement (calm, excitement). The literature presents ways of evaluating emotional cues, with inference in real time, by collecting physiological signals through sensors and classified by algorithms in the emotional domains of Valencia and Excitation. In this context, there is a complexity in collecting this data with low-cost sensors, as well as classifying emotions into more emotional domains, increasing the number of classes and consequently the accuracy of the classification in space. This dissertation aimed to classify physiological signals collected with low cost commercial sensors, inferring dimensional emotions in four domains: Valencia, Excitation, Feeling of control and Ease of conclusion of the objective. Thus, this work presents a dataset, with data from three sensors: cardiac activity (ECG), brain activity (EEG) and galvanic response (GSR). To compose the dataset, the physiological signals were collected from 33 participants in three sessions. In order to bring the individual to a desired emotional state, 16 prelabeled movie clips and video clips were used. After the collection and recording of the signals, a preprocessing step was performed to eliminate noise and inconsistent data and extraction of characteristics. In order to classify, we used the closest K-neighbors algorithms, Naive Bayes, Decision Tree, Random Forest, XGBoost, Support Vector Machine and Artificial Neural Networks. Finally, a statistical evaluation of the performance of the algorithms in each sensor data was performed. The classification algorithms that best fit the characteristics of the data were Naive Bayes for ECG and GSR with 96% and 77% accuracy and Support Vector Machine for EEG with 99% accuracy. The results suggest that the data collected allow classification in the four domains studied.

The Internet of Things allowed the creation of a set of computer systems embedded in everyday objects such as clothes, toys and home appliances. Some of these systems are not just for use but offer possibilities for customization through programming. However, especially for specific audiences, such as small children (4 to 6 years), this universe of differentiated interactions, in which different intelligent devices with particular specifications coexist, may require greater cognitive effort, making it difficult to use programming functionalities. In this scenario, this work presents an interaction model to guide the provision of programming devices for children. For the construction of this model, specified and represented in the Stamper´s Semiotic Ladder, a state-of-the-art survey was performed on the programming of physical devices by infants in early childhood and a case study using Participatory Design techniques with the participation of children between 4 and 6 years old. A feasibility study conducted with a paper-based prototype indicated that children can control devices from programming environments built following the model.

[colocar o In recent years there has been a breakthrough in the development of technologies that have digitized the listening experience of music. With this, a large collection of music became available on the internet, in addition to the emergence of new automated techniques of music selection. Current music playback systems retrieve music through metadata such as title, author, band, and music genre. Since music can convey information related to emotion, studies show that music is an effective means of emotional induction and can change the emotional behavior of the user. The current methods of music recommendation and playback depending on the emotion requires a manual user interaction and are often suggested from a set of already pre-sorted songs, so this becomes a problem for the user, since most of the time the user has an intensive task in selecting a song according to the desired emotion before a large set of diverse songs and varied styles. Thus, this work aims to propose m-Motion, a musical reproduction tool for smartphones that seeks to help the user achieve a desired emotional state from their current emotional state. The current and desired emotion of the user is obtained by the expression of subjective feelings, informed through the speech of the voice (text) and of an element of user interface inspired in the semantic space of Scherer. The emotion of the user's songs are mapped to a dimensional space of excitation and valence, which are predicted by the classification algorithm Support Vector Machine (SVR). Therefore, this work adopted the semantic space of Scherer to classify the emotions of the songs and the users in terms of excitement and valence. Thus, the m-Motion algorithm makes use of two mathematical formulas, being the Euclidean distance and the equation of the line between the current and desired emotion. With this, the algorithm is able to return a set of songs between the current and desired emotion of the user. An experiment was conducted with three distinct groups of users that aimed to assess the emotion achieved by users after playing a set of suggested songs. The first two groups had 20 users each experiment and therefore each user was collected the current and desired emotional state, as well as the facial expressions during music playback. The first group received suggestions of songs returned by the proposed algorithm, while the second group the songs were manually suggested by the user. The third group contained 8 users and the experiment was carried out outside the controlled environment. Users of this group used the m-Motion application for 5 days and received music suggestions based on the desired emotional state. The results suggest that, when listening to the songs selected by the proposed application, the users can approach the desired emotional state, as well as the manual recommendation made by the user. todo...] compared to other website builders, analyzing load times, responsiveness, and SEO effectiveness.c

With the advancement of computational technologies, several areas of knowledge have enjoyed more and more of their benefits. One of the benefits that this technological advance has brought, within the area of health are the therapeutic digital games. They help hide the burden of the therapeutic tasks behind a fantasy world, raising motivation and adherence to therapy. However, the design of this category of games is more complex when compared to the design of conventional digital games. Because it is in a multidisciplinary context, it can be said that it is not enough just to have knowledge of game development, being also necessary to have knowledge about the pathology to be attended to and the domain that surrounds it. To date, no formalized methodology for the design of therapeutic digital games has been found in the literature that considers a multidisciplinary team and covers all stages of the design process. With this, this dissertation aims to formalize an semi-participatory approach for the design of therapeutic digital games, providin the participation of computer and health professionals in all stages of the design of a therapeutic game and facilitate communication between the stakeholders through well defined steps and activities. For this, a Systematic Review of the literature was initially undertaken to understand how existing therapeutic digital games were developed. Also as part of the baseline studies, a group of researchers who developed a game for patients with depression was studied, generating an account of experience. An initial version of the approach was presented to students of the Graduate Program in Nursing and applied by students of the Graduate Program in Computing, seeking to obtain feedback from these two groups in relation to the approach. After refinement of the approach, it was applied in the construction of a therapeutic digital game for the children and family attended by Hospital do Amor of the Barretos and evaluated by the professionals involved. The approach was named by SemTh, name inspired by the terms "Semio-participatory" and "Therapeutic Games". The SemTh is organized in four steps for the design, being: 1) Design Problem Clarification, where it is sought to understand the domain and propose the style of the game; 2) Interaction modeling, where the interactions of the game are modeled; 3) Design Materialization, where prototypes are created and the game is implemented; and 4) Evaluation, in this stage the game is evaluated by the team and by the end users. The evaluation of the approach was carried out in a qualitative way, through a questionnaire applied to professionals in the areas of computing and health, who participated in the game design for Hospital do Amor. The results of the evaluation pointed out that with the proposed approach it was possible to direct the computer team and empower the health team during the design of the therapeutic digital game.

To address the diversity of users and the different interaction requirements, the user interfaces could be more flexible, being adapted according to each user profile. Currently, some web interfaces are already flexible, but this flexibility is usually made from explicitly made adjustments by the user in each website. The flexibility achieved by the interfaces of the current websites is not enough when the diversity of users and different interaction needs are considered. In addition, to adapt a web system, currently the user has to configure each system individually and not all users are aware of the different possibilities of presentation and configuration of the websites. Since the interfaces must be flexible to meet the different needs and diversity of users, this work aims to provide users with the possibility to adapt the websites according to their needs and preferences. To achieve this goal, an approach was formalized where the user defines his interaction profile, based on rules, guidelines and good design recommendations, and later this interaction profile is used to adapt the interfaces. In addition, the UIFlex tool was developed, where the user defines their interaction profile and, from this profile, the tool flexibilizes the interfaces of the websites that users navigate according to the interaction profile defined by the user. Finally, two evaluations were carried out in different scenarios: one face-to-face and the other online. These evaluations were carried out with the purpose of verifying the viability of the UIFlex tool and whether it meets the diversity of users. In both scenarios, users accessed certain websites with and without the UIFlex tool and subsequently answered questionnaires related to user satisfaction, website behavior and interaction efficiency. The results of the questionnaires answered indicated that the UIFlex tool brings benefits during the interaction of the users with the websites, mainly related to the efficiency, due to the adaptation made in the websites by the tool, without the need to configure each website individually. With the studies carried out and with the analysis of the answers of the questionnaires it is concluded that the UIFlex tool contributed positively to the users adapting the interfaces of the websites according to their preferences and/or needs.

Emotions play a crucial role in the way people interact with each other, objects and computing systems, and are a key factor in human-computer interaction. The choice of the appropriate elements for a user interface may result in a better experience of how it can be used. However, most studies investigate people’s preferences and visual aesthetics, without taking into account people’s emotion in the design. This dissertation carries out a series of detailed studies on the emotional effects of user interface elements, by examining colors, fonts and images. A critical analysis of the literature (through a systematic review) combined to the Semantic Space of Emotions, which covers a broad spectrum of emotions, resulted in the proposal of Bianchi’s Color Wheel. An empirical study was conducted on the emotional effects of font types and sizes; this involved 60 users and was necessary because there are so few studies on fonts and emotions in the literature. With regard to font types, in statistical terms, it was found there were no significant differences, although Arial was more closely linked to positive emotions than Times New Roman in the discourse analysis. Small font sizes, 8pt, caused negative experiences and led to tiredness, while medium (12pt) and large (16pt) sizes were mainly related to pleasant and comforting experiences. The third study investigated tagged and felt emotions evoked by images which were collected through social tags that were clearly related to emotions. The aim of the study was to determine whether or not these images are reliable for the design and retrieval. Thus, an online survey was planned and carried out by a group of 410 volunteers who classified pictures from Flickr. The results suggested that there are some emotions tagged that were similar to observers emotions, while others are diffuse and need other criteria for their selection apart from social tags. Finally, it should be mentioned that further studies are needed to address the complete user interface with all these elements and findings combined.

Emotion is an important factor in Human-Computer Interaction (HCI) that influences users’ behavior and satisfaction. Empirical methods, i.e., when users are directly involved, are often applied to assess emotional responses evoked by the user interface, but the cost of data collection and analysis is generally high. The adoption of analytical methods is an alternative to the high cost. Although analytical methods are widely accepted in the HCI area, there is a lack of analytical evaluations for emotional responses. The proposed analytical method in this work adopts the semiotic framework and Peirce’s ten classes of signs for the analysis of the design proposal and by the Scherer’s Semantic Space of Emotions for the association of possible emotional responses evoked by the interface signs. The current version of the proposed method was applied to a case study and results were considered consistent when compared with those obtained through empirical methods