Submitted by PPG Ci?ncia da Computa??o (ppgcc@pucrs.br) on 2018-06-19T12:02:08Z No. of bitstreams: 1 CAROLINE_QUEIROZ_SANTOS_TES.pdf: 16112949 bytes, checksum: fe22f5c9acd1d52e51f0dcfb05c80e68 (MD5) / Approved for entry into archive by Sheila Dias (sheila.dias@pucrs.br) on 2018-06-27T11:19:29Z (GMT) No. of bitstreams: 1 CAROLINE_QUEIROZ_SANTOS_TES.pdf: 16112949 bytes, checksum: fe22f5c9acd1d52e51f0dcfb05c80e68 (MD5) / Made available in DSpace on 2018-06-27T11:39:56Z (GMT). No. of bitstreams: 1 CAROLINE_QUEIROZ_SANTOS_TES.pdf: 16112949 bytes, checksum: fe22f5c9acd1d52e51f0dcfb05c80e68 (MD5) Previous issue date: 2018-04-12 / The analysis of data from social media has been a growing practice, making data visualization an important aspect in the context of presenting the large volumes of data typically extracted from these media. One of the challenges in this area is the efficient presentation of these large volumes of data, providing techniques that support the design processes, analysis and understanding of these data. Moving forward in this direction, this thesis presents CIViS, a customizable interface design model to support the construction of interactive narrative visualizations of data extracted from social media. It is a descriptive model, based on the theory of Semiotic Engineering and its view on End-user Development, as well as on narrative visualization concepts. The model considers that the social-media data analyst has interest in organizing his/her data presentation in such a way to tell a story with them. Thus, CIViS proposes a set of components that structure the design space, with the purpose of assisting designers and data analysts as co-designers to reflect on different aspects that influence the construction of customizable interactive narrative visualizations. We carried out four studies and, based on the results triangulation, we obtained the bases for consolidating the idea of the model, continuing with its creation. After conceiving the CIViS model, we conducted a study focusing on the use of the model by social-media data analysts. With the conclusion of the study of use of the CIViS, we obtained results that indicate pertinent ways of representing relevant narrative aspects. We have also verified that the model is satisfactorily descriptive to assist in the design of visualizations, whether narrative or not. Finally, we present the potential epistemic value of the CIViS, considering that its use can instigate important discussions and reflections during the process of designing customizable interactive narrative visualizations, assisting both designers and co designers in its epistemic character. / A an?lise de dados de m?dias sociais tem sido uma pr?tica crescente, tornando a visualiza??o de dados um aspecto importante no contexto de apresenta??o dos grandes volumes de dados tipicamente extra?dos dessas m?dias. Um dos desafios nesta ?rea est? na apresenta??o eficiente desses grandes volumes de dados, provendo t?cnicas que apoiem os processos de design, an?lise e compreens?o destes dados. Avan?ando neste sentido, esta tese apresenta o CIViS, um modelo de design de interface customiz?vel para apoiar a constru??o de visualiza??es narrativas interativas de dados extra?dos de m?dias sociais. Trata-se de um modelo descritivo, fundamentado na teoria da Engenharia Semi?tica e sua vis?o sobre End-user Development, assim como em conceitos de visualiza??o narrativas. O modelo considera que o analista de dados de m?dias sociais tem interesse em organizar a apresenta??o de seus dados de forma a contar uma hist?ria com eles. Assim, o CIViS prop?e um conjunto de componentes que estruturam o espa?o de design, tendo o prop?sito de auxiliar designers e analistas de dados co-designers a refletirem sobre diferentes aspectos que influenciam a constru??o de visualiza??es narrativas interativas customiz?veis. Realizamos quatro estudos e, a partir da triangula??o dos resultados, obtivemos subs?dios para a consolida??o da ideia do modelo, dando prosseguimento ? sua cria??o. Ap?s a concep??o do modelo CIViS, realizamos um estudo com foco no uso do modelo por analistas de dados de m?dias sociais. Com a conclus?o do estudo de uso do CIViS, obtivemos resultados que sinalizam formas pertinentes de representar aspectos relevantes de narrativas. Tamb?m verificamos que o modelo ? satisfatoriamente descritivo para auxiliar no design de visualiza??es, sejam elas narrativas ou n?o. Por fim, apresentamos o potencial valor epist?mico do CIViS, considerando que seu uso pode instigar discuss?es e reflex?es importantes durante o processo de design de visualiza??es narrativas interativas customiz?veis, atendendo tanto designers quanto co-designers em seu car?ter epist?mico.

Recent innovations in the information technology and computing devices magnified the volume of available information. Today’s decision makers face the challenge of analyzing ever more data in shorter timeframes. Demand for technology that can efficiently assist systematic data analysis is constantly growing. Development of dedicated information systems is, however, difficult both from organizational and technological point of view. First, traditional software production is a complex and time-consuming process that can not be performed under time-pressure. Second, changing business conditions and evolving stakeholder needs require solutions that can be efficiently tailored over time. Finally, costs of custom software development are high, so that not all use cases and scenarios can be covered sufficiently. This thesis proposes a holistic approach to address the challenges above and to enable efficient development of decision support software. The main idea is to empower end users, i.e., decision makers, in constructing their own case-specific solutions. The proposed approach called Web-Composition for End-User Development consists of a systematic process for development and evolution of decision support systems, assistance mechanisms to address lack of programming skills by decision makers and evolution facilities to enable cost- and time-efficient extensibility of user-produced solutions. The thesis describes implementation of the devised principles and ideas in the context of several open-source projects and application scenarios. Applicability and usability of the concepts are demonstrated in user studies with respective target groups. Based on the outcome analysis the thesis concludes that end users can and should actively participate in construction of decision support software.

Cette thèse traite du problème du développement d'espaces intelligents par l'utilisateur final sous l'angle de l'Interaction Homme-Machine et de l'Intelligence Ambiante. Dans les processus actuels de développement, l'utilisateur est un consommateur contraint par un système pensé et réalisé par d'autres. L'objectif de cette thèse est de redonner le pouvoir à l'utilisateur final par le biais d'outils adaptés au développement d'espaces intelligents. Cette thèse retient l'habitat intelligent comme lieu de vie privilégié. Ses contributions incluent : (1) DisQo (Dispositifs du QuOtidien), une nouvelle méthode d'investigation des besoins, réalisable au domicile de familles, qui sollicite l'imagination et assure un juste équilibre entre contrôle expérimental, respect de la sphère privée et validité écologique des résultats ; (2) Un espace de classification pour une lecture comparative systématique et synthétique des outils portant sur le développement et la programmation d'habitats intelligents. Cette taxonomie met en évidence le peu d'avancées en édition multisyntaxe de même pour l'aide à la mise au point de programmes ; (3) KISS (Knit Your Ideas into Smart Spaces), un outil de programmation et de mise au point dont le langage de programmation est de type déclaratif orienté règles, avec potentiel d'égale opportunité syntaxique entre langue française pseudonaturelle (LPN) et langage visuel iconique. La technique d'interaction de construction des programmes LPN s'appuie sur l'utilisation de menus dont les options sont calculées dynamiquement assurant ainsi la découverte progressive du langage ainsi que l'extensibilité et la correction syntaxique et sémantique des programmes. La mise au point peut se pratiquer, au choix, dans le monde physique ou dans un monde dual numérique. L'évaluation de KISS dans DOMUS, un habitat intelligent d'expérimentation, montre que les utilisateurs parviennent à programmer un scénario réaliste de la vie réelle. / This dissertation addresses the problem of end-user development for smart spaces from a human-computer interaction perspective in the context of ambient intelligence. End-users are currently doomed to be consumers of systems that have been designed and implemented by others. The goal of this thesis is to provide end-users with tools that will enable them to develop their own smart spaces. This work focuses on the home as a key place for smartness. The contribution of this doctoral research is threefold: (1) DisQo, a new method for field studies that combines several techniques to reach a satisfying balance between experimental control, privacy issues, and ecological validity. Its key element is for observers to be able to “visit” people homes through the pictures of intimate objects taken by the participants themselves and to use these pictures as playful cultural probes to envision future use; (2) A problem space that makes explicit the functional coverage (as well as the limits) of the tools from the state of the art in the area of end-user development for smart homes. In particular, the problem space reveals a lack of support for multi-syntax editing as well as for testing and debugging programs; (3) KISS (Knit your Ideas into Smart Spaces), an end-user development tool that uses a declarative rule-based programming paradigm where programs are expressed in a French pseudo-natural language with potentiality for syntactic equal opportunity with an iconic visual language. Programs are constructed by selecting items from pull down menus that are dynamically updated with the functionalities of the smart home. By so doing, the end-user can learn the programming language incrementally and specify programs that are semantically and syntactically correct. Programs can be tested either in a virtual home or in a real home. The evaluation of KISS in the DOMUS experimental platform, shows that users are able to program a real-life scenario.