Personalized Human-Computer Interaction

The three volume set provides a systematic overview of theories and technique on social network analysis. Volume 1 of the set mainly focuses on the structure characteristics, the modeling, and the evolution mechanism of social network analysis. Techniques and approaches for virtual community detection are discussed in detail as well. It is an essential reference for scientist and professionals in computer science. Personalized and adaptive systems employ user models to adapt content, services, interaction or navigation to individual users' needs. User models can be inferred from implicitly observed information, such as the user's interaction history or current location, or from explicitly entered information, such as user profile data or ratings. Applications of personalization include item recommendation, location-based services, learning assistance and the tailored selection of interaction modalities. With the transition from desktop computers to mobile devices and ubiquitous environments, the need for adapting to changing contexts is even more important. However, this also poses new challenges concerning privacy issues, user control, transparency, and explainability. In addition, user experience and other human factors are becoming increasingly important. This book describes foundations of user modeling, discusses user interaction as a basis for adaptivity, and showcases several personalization approaches in a variety of domains, including music recommendation, tourism, and accessible user interfaces. The goal of this book is to provide a mathematical perspective on some key elements of the so-called deep neural networks (DNNs). Much of the interest in deep learning has focused on the implementation of DNN-based algorithms. Our hope is that this compact textbook will offer a complementary point of view that emphasizes the underlying mathematical ideas. We believe that a more foundational perspective will help to answer important questions that have only received empirical answers so far. The material is based on a one-semester course Introduction to Mathematics of Deep Learning" for senior undergraduate mathematics majors and first year graduate students in mathematics. Our goal is to introduce basic concepts from deep learning in a rigorous mathematical fashion, e.g introduce mathematical definitions of deep neural networks (DNNs), loss functions, the backpropagation algorithm, etc. We attempt to identify for each concept the simplest setting that minimizes technicalities but still contains the key mathematics. Introduction Contents List of Contributing Authors Part I: Foundations of personalization 1 Theory-grounded user modeling for personalized HCI 2 User-centered recommender systems 3 Fairness of information access systems Part II: User input and feedback 4 Personalization and user modeling for interaction processes 5 How to use socio-emotional signals for adaptive training 6 Explanations and user control in recommender systems 7 Feedback loops and mutual reinforcement in personalized interaction Part III: Personalization purposes and goals 8 Personalizing the user interface for people with disabilities 9 Personalized persuasion for behavior change 10 Personalization approaches for remote collaborative interaction Part IV: Personalization domains 11 Listener awareness in music recommender systems: directions and current trends 12 Tourist trip recommendations – foundations, state of the art and challenges 13 Pictures as a tool for matching tourist preferences with destinations Index