The mobile era is well established and the number of smartphone users is showing exponential growth. The capability of smartphones and enabling technologies is also increasing and has opened many possibilities of personalized mobile services. The goal of personalization is to support the user by providing the right service at the rightmoment. Early focus of personalization was on content adaptations in different information systems. The new approaches of personalization are still needed for mobileservices as it is a compelling feature of mobile communication systems for both endusers and service providers.Personalization is providing a means of fulfilling users’ needs more effectively andefficiently and, consequently increasing users’ satisfaction. By providing successfulpersonalization, a high degree of user satisfaction and a pleasant user experience can beachieved. Some features of personalization can cause problems and may outweigh thebenefits of personalization.This thesis has focused on how to achieve scrutable mobile client-side personalizationwhile keeping the user’s privacy. The issue of privacy in personalization of mobileservices can be reduced by shifting the control of their personal information towards theusers. Our research goal is to understand and improve the personalization process anddevelop an architecture for scrutable mobile client-side personalization while keepingthe user s’ privacy. Moreover, there is a need to develop an evaluation framework tomeasure the effectiveness of mobile services personalization. A design science researchmethodology is adopted in this research work. More particular contributions of thethesis are as follows: C1: Identifications of the research issues and challenges in personalization of mobileservices. C2: An approach for delivering personalized mobile services. C3: Development of mobile client-side personalization architecture. C4: Development of mobile services Personalization Evaluation Model. C5: Identification of the prospects of scrutable personalization of mobile services.

"After decades of development, Intelligent Tutoring Systems (ITSs) have become a common learning environment for learners of various domains and academic levels. ITSs are computer systems designed to provide instruction and immediate feedback, which is customized to individual students, but without requiring the intervention of human instructors. All ITSs share the same goal: to provide tutorial services that support learning. Since learning is a very complex process, it is not surprising that a range of technologies and methodologies from different fields is employed. Student modeling is a pivotal technique used in ITSs. The model observes student behaviors in the tutor and creates a quantitative representation of student properties of interest necessary to customize instruction, to respond effectively, to engage students¡¯ interest and to promote learning. In this dissertation work, I focus on the following aspects of student modeling. Part I: Student Knowledge: Parameter Interpretation. Student modeling is widely used to obtain scientific insights about how people learn. Student models typically produce semantically meaningful parameter estimates, such as how quickly students learn a skill on average. Therefore, parameter estimates being interpretable and plausible is fundamental. My work includes automatically generating data-suggested Dirichlet priors for the Bayesian Knowledge Tracing model, in order to obtain more plausible parameter estimates. I also proposed, implemented, and evaluated an approach to generate multiple Dirichlet priors to improve parameter plausibility, accommodating the assumption that there are subsets of skills which students learn similarly. Part II: Student Performance: Student Performance Prediction. Accurately predicting student performance is one of the most desired features common evaluations for student modeling. for an ITS. The task, however, is very challenging, particularly in predicting a student¡¯s response on an individual problem in the tutor. I analyzed the components of two common student models to determine which aspects provide predictive power in classifying student performance. I found that modeling the student¡¯s overall knowledge led to improved predictive accuracy. I also presented an approach, which, rather than assuming students are drawn from a single distribution, modeled multiple distributions of student performances to improve the model¡¯s accuracy. Part III: Wheel-spinning: Student Future Failure in Mastery Learning. One drawback of the mastery learning framework is its possibility to leave a student stuck attempting to learn a skill he is unable to master. We refer to this phenomenon of students being given practice with no improvement as wheel-spinning. I analyzed student wheel-spinning across different tutoring systems and estimated the scope of the problem. To investigate the negative consequences of see what wheel-spinning could have done to students, I investigated the relationships between wheel-spinning and two other constructs of interest about students: efficiency of learning and ¡°gaming the system¡±. In addition, I designed a generic model of wheel-spinning, which uses features easily obtained by most ITSs. The model can be well generalized to unknown students with high accuracy classifying mastery and wheel-spinning problems. When used as a detector, the model can detect wheel-spinning in its early stage with satisfying satisfactory precision and recall. "

The thesis addresses three main problems in the area of user modeling and adaptation in the context of online communities:<p> 1) Dealing with unique and changing user modeling needs of online communities. <p> 2) Involving users in design of the user modeling process.<p> 3) Interoperability of user models across different communities.<p> A new policy based-approach for user modeling is proposed, that allows explicit declarative representation of the user modeling and adaptation process in terms of policies, which can be viewed and edited by users. This policy-based user model framework is implemented in the MCComtella community framework, developed as part of this thesis work, which allows hosting multiple communities, creating new communities by users, and which supports users in setting explicit user modeling policies defining participation rewards, roles and movement of users across communities.

The thesis addresses three main problems in the area of user modeling and adaptation in the context of online communities:<p> 1) Dealing with unique and changing user modeling needs of online communities. <p> 2) Involving users in design of the user modeling process.<p> 3) Interoperability of user models across different communities.<p> A new policy based-approach for user modeling is proposed, that allows explicit declarative representation of the user modeling and adaptation process in terms of policies, which can be viewed and edited by users. This policy-based user model framework is implemented in the MCComtella community framework, developed as part of this thesis work, which allows hosting multiple communities, creating new communities by users, and which supports users in setting explicit user modeling policies defining participation rewards, roles and movement of users across communities.

It is the underlying presupposition of the Science Assistments research (http://www.scienceassistments.org) that students need to leave school with a basic understanding of science and grounding in inquiry skills (NSES, 1996; NRC, 2011). We also believe that the current standard for assessing these skills, the Massachusetts Comprehensive Assessment System, is inadequate in terms of the rote- oriented multiple-choice tests. This thesis describes the creation of a simulation, or microworld, of an animal cell. This content is aligned with the Massachusetts science frameworks for middle school Life Science (Massachusetts Department of Education, 2006). Our microworld, Simcell, gives students an opportunity to form hypotheses, design experiments to test these hypotheses, and analyze their data collected during the experiment. The microworlds track students' actions in log files that can be analyzed by the system to provide fine tuned assessments of students, and based on these assessments, in the future, we will provide dynamic help though scaffolds to students who are struggling with inquiry (Gobert et al, 2007; 2009; Gobert et al, in press). Over the course of two studies, this biology microworld was designed, developed, and fined tuned through the use of domain experts and student pilot data. We also analyzed the student logs in order to try to model students' learning so we can predict useful times for the system to come in and help. In study one we identify a potential point to remediate struggling students. In study two we conducted a series of logistic and linear regressions to predict student knowledge. However, due to the large number of different variables and the relatively small size of the dataset, we could not be confident in the results that were obtained. Many attempts to reduce the number of variables used in the model were tried, but these methods did not yield more promise than the original set. Finally, we finish this report with a new path for researchers to consider, namely, looking at the data in different ways in order to find a way of viewing the data that would allow for known successful student modeling techniques such as Bayesian Knowledge Tracing.

This thesis describes an Intelligent Tutoring System developed to be used in distance education at Master&rsquo / s level. The system was designed and implemented to help teachers to generate course material for online tutoring and to help the students to navigate through the course material according to their knowledge level. The system integrates many new technologies and provides individualized learning for students which is one of the most efficient ways for learning. How well the student has learned the course material is tested immediately after each smallest learning unit by end-of-section tests and the knowledge level of the student is derived from the answers given to these tests. This knowledge level is used to build a user model. This thesis describes how this user model is used for navigational support for students while studying on the course material.

Abstract The focus of this thesis is to assess factors which have an influence on the acceptance of personalized Web information systems (WIS). This study is primarily based on the widely used and accepted Technology Acceptance Model (TAM). The qualitative part of the study presents an approach for developing dynamic Web information systems. The development process was based on the work done in the OWLA (Open Web/Wireless Adaptive Hypermedia Applications) research project in 2000–2002. The quantitative part of the study, which includes the main objective of the study, is related to assessment of user acceptance of the given system. The researcher performed a field study in 2003 in which data was collected using a web questionnaire. The field study resulted in a sample size of 209 responses. Moreover we carried out a comparison with the 2002/2003 field study aiming to study possible differences in respondents' attitude toward personalization. The previous field study was carried out during the OWLA research project. The responses were analyzed using SPSS and AMOS. Results of the quantitative part of the study show that the respondents accept personalization but they like to and want to adapt and personalize the content themselves. This was one of the most important findings of the study. Respondents do not want the system to provide content automatically; they want to control the content themselves. The results of the 2003 field study indicate that respondents do not consider layout adaptation, whether automatic or manual, to be important or desirable. The formulated model reveals that perceived relevance is one of the most important aspects that have an effect on attitude toward using and intention to use the given IS. Perceived expectancy and intention to use the given WIS are significant antecedents of actual use. Perceived behavioral control and normative beliefs also have a significant effect on intention to use portal. Enjoyment has a significant effect on attitude. Overall, we have identified in this study some significant factors which will provide useful information to IS practitioners studying the voluntary adoption of specific personalized systems. The results will also provide useful information for systems designers and will contribute towards assessing possible individual barriers to the use of personalized information systems. The study includes several proposals for future research including developing deeper understanding activities related to presented development approach, creating a more detailed view of factors which have an influence on the user's decision to use or not to use personalized information system, studying several systems.

Social media services have a growing impact in our society. Individuals often rely on social media to get their news, decide which products to buy or to communicate with their friends. As consequence of the widespread adoption of social media, a large volume of data on how users behave is created every day and stored into large databases. Learning how to analyze and extract useful knowledge from this data has a number of potential applications. For instance, a deeper understanding on how legitimate users interact with social media services could be explored to design more accurate spam and fraud detection methods. This PhD research is based on the following hypothesis: data generated by social media users present patterns that can be exploited to improve the effectiveness of tasks such as prediction, forecasting and modeling in the domain of social media. To validate our hypothesis, we focus on designing data mining methods tailored to social media data. The main contributions of this PhD can be divided into three parts. First, we propose Act-M, a mathematical model that describes the timing of users actions. We also show that Act-M can be used to automatically detect bots among social media users based only on the timing (i.e. time-stamp) data. Our second contribution is VnC (Vote-and-Comment), a model that explains how the volume of different types of user interactions evolve over time when a piece of content is submitted to a social media service. In addition to accurately matching real data, VnC is useful, as it can be employed to forecast the number of interactions received by social media content. Finally, our third contribution is the MFS-Map method. MFS-Map automatically provides textual annotations to social media images by efficiently combining visual and metadata features. Our contributions were validated using real data from several social media services. Our experiments show that the Act-M and VnC models provided a more accurate fit to the data than existing models for communication dynamics and information diffusion, respectively. MFS-Map obtained both superior precision and faster speed when compared to other widely employed image annotation methods. / O impacto dos serviços de mídia social em nossa sociedade é crescente. Indivíduos frequentemente utilizam mídias sociais para obter notícias, decidir quais os produtos comprar ou para se comunicar com amigos. Como consequência da adoção generalizada de mídias sociais, um grande volume de dados sobre como os usuários se comportam é gerado diariamente e armazenado em grandes bancos de dados. Aprender a analisar e extrair conhecimentos úteis a partir destes dados tem uma série de potenciais aplicações. Por exemplo, um entendimento mais detalhado sobre como usuários legítimos interagem com serviços de mídia social poderia ser explorado para projetar métodos mais precisos de detecção de spam e fraude. Esta pesquisa de doutorado baseia-se na seguinte hipótese: dados gerados por usuários de mídia social apresentam padrões que podem ser explorados para melhorar a eficácia de tarefas como previsão e modelagem no domínio das mídias sociais. Para validar esta hipótese, foram projetados métodos de mineração de dados adaptados aos dados de mídia social. As principais contribuições desta pesquisa de doutorado podem ser divididas em três partes. Primeiro, foi desenvolvido o Act-M, um modelo matemático que descreve o tempo das ações dos usuários. O autor demonstrou que o Act-M pode ser usado para detectar automaticamente bots entre usuários de mídia social com base apenas nos dados de tempo. A segunda contribuição desta tese é o VnC (Vote-and- Comment), um modelo que explica como o volume de diferentes tipos de interações de usuário evolui ao longo do tempo quando um conteúdo é submetido a um serviço de mídia social. Além de descrever precisamente os dados reais, o VnC é útil, pois pode ser empregado para prever o número de interações recebidas por determinado conteúdo de mídia social. Por fim, nossa terceira contribuição é o método MFS-Map. O MFS-Map fornece automaticamente anotações textuais para imagens de mídias sociais, combinando eficientemente características visuais e de metadados das imagens. As contribuições deste doutorado foram validadas utilizando dados reais de diversos serviços de mídia social. Os experimentos mostraram que os modelos Act-M e VnC forneceram um ajuste mais preciso aos dados quando comparados, respectivamente, a modelos existentes para dinâmica de comunicação e difusão de informação. O MFS-Map obteve precisão superior e tempo de execução reduzido quando comparado com outros métodos amplamente utilizados para anotação de imagens.

Depuis l'explosion du Web, la Recherche d'Information (RI) s'est vue étendue et les moteurs de recherche sur le Web ont vu le jour. Les méthodes classiques de la RI, surtout destinées à des recherches textuelles simples, se sont retrouvées face à des documents de différents formats et des contenus riches. L'utilisateur, en réponse à cette avancée, est devenu plus exigeant quant aux résultats retournés par les systèmes de RI. La personnalisation tente de répondre à ces exigences en ayant pour objectif principal l'amélioration des résultats retournés à l'utilisateur en fonction de sa perception et de ses intérêts ainsi que de ses préférences. Le présent travail de thèse se situe à la croisée des différents aspects présentés et couvre cette problématique. Elle a pour objectif principal de proposer des solutions nouvelles et efficaces à cette problématique. Pour atteindre cet objectif, un système de personnalisation de la recherche spatiale et sémantique sur le Web et intégrant la modélisation de l'utilisateur, a été proposé. Ce système comprend deux volets : 1/ la modélisation de l'utilisateur ; 2/ la collaboration implicite des utilisateurs à travers la construction d'un réseau de modèles utilisateurs, construit itérativement lors des différentes recherches effectuées en ligne. Un prototype supportant le système proposé a été développé afin d'expérimenter et d'évaluer l'ensemble de la proposition. Ainsi, nous avons effectué un ensemble d'évaluation, dont les principales sont : a) l'évaluation de la qualité du modèle de l'utilisateur ; b) l'évaluation de l'efficacité de la recherche d'information ; c) l’évaluation de l'efficacité de la recherche d'information intégrant les informations spatiales ; d) l'évaluation de la recherche exploitant le réseau d'utilisateurs. Les expérimentations menées montrent une amélioration de la personnalisation des résultats présentés par rapport à ceux obtenus par d'autres moteurs de recherche. / The web explosion has led Information Retrieval (IR) to be extended and web search engines emergence. The conventional IR methods, usually intended for simple textual searches, faced new documents types and rich and scalable contents. The users, facing these evolutions, ask more for IR systems search results quality. In this context, the personalization main objective is improving results returned to the end user based sing on its perception and its interests and preferences. This thesis context is concerned with these different aspects. Its main objective is to propose new and effective solutions to the personalization problem. To achieve this goal, a spatial and semantic web personalization system integrating implicit user modeling is proposed. This system has two components: 1/ user modeling; /2 implicit users' collaboration through the construction of a users' models network. A system prototype was developed for the evaluation purpose that contains: a) user model quality evaluation; b) information retrieval quality evaluation; c) information retrieval quality evaluation with the spatial user model data; d) information retrieval quality evaluation with the whole user model data and the users' models network. Experiments showed amelioration in the personalized search results compared to a baseline web search.

In my teaching and software development practice, I realized that most applications with human-computer interaction do not respond to users’ emotional needs. The dualism of reason and emotion as two fairly opposite entities that dominated Western philosophy was also reflected in software design. Computing was originally intended to provide applications for military and industrial activities and was primarily associated with cognition and rationality. Today, more and more computer applications interact with users in very complex and sophisticated ways. In human-computer interaction, attention is given to issues of usability and user modeling, but techniques to emotionally engage users or respond to their emotional needs have not been fully developed, even as specialists like Klein, Norman and Picard argued that machines that recognize and express emotions respond better and more appropriately to user interaction (Picard, 1997; Picard & Klein, 2002; Norman, 2004). This study investigated emotion from designers’ perspectives and tentatively concludes that there is little awareness and involvement in emotional design in the IT community. By contrast, participants in this study (36 IT specialists from various fields) strongly supported the idea of emotional design and confirmed the need for methodologies and theoretical models to research emotional design. Based on a review of theory, surveys and interviews, I identified a set of themes for heuristics of emotional design and recommended future research directions. Attention was given to consequences; participants in this study raised issues of manipulation, ethical responsibilities of designers, and the need for regulations, and recommended that emotional design should carry standard ethical guidelines for games and any other applications. The research design utilized a mixed QUAN-qual methodological model proposed by Creswell (2003) and Gay, Mills, and Airasian (2006), which was modified to equally emphasize both quantitative and qualitative stages. An instrument in the form of a questionnaire was designed, tested and piloted in this study and will be improved and used in future research.