Interacting with Recommender Systems
Dietmar Jannach (TU Dortmund)
Ingrid Nunes (Federal University of Rio Grande do Sul, Brazil)
Michael Jugovac (TU Dortmund, Germany)
Short biography of the Presenter
Dietmar Jannach is a full professor of computer science at TU Dortmund, Germany, and the leading author of the textbook "Recommender Systems – An Introduction" published by Cambridge University Press. Ingrid Nunes is a "professor adjunto" of computer science at the Federal University of Rio Grande do Sul, Brazil. Her research in the area of decision support systems and recommender systems focuses on explanation and preference modeling, and natural-language based systems.
Michael Jugovac is a PhD student in the research group of Dietmar Jannach, working on the topic of interactive recommender systems.
Today's recommender systems mostly implement a one-shot interaction design, and users are typically only provided with a limited number of ways to interact with the system. However, in academic research a variety of interaction mechanisms for recommender systems have been proposed over the years, which are designed, for example, to allow users to refine their preferences, to interactively explore the space of alternatives, or to give the system feedback on the recommendations. In this tutorial we will review approaches from academia and industry for building more interactive recommender systems using, e.g., different visualizations or explanations, and outline the open challenges in the field.
Creating Custom Wearable Electronics: From Design to Fabrication to Experimentation
Charles Callaway (FBK-irst)
Dr. Charles Callaway is a researcher with over 20 years of experience in Artificial Intelligence and Computational Linguistics. First publishing at IUI in 1998, he is now a senior member of the IUI program committee. His interests include mobile and group interaction, tutoring systems, user modelling, and natural language dialogue and generation. He has worked for the last 8 years in the area of mobile platforms, ambient intelligence and portable sensors.
Wearables offer an attractive platform for interacting intelligently with our environment and ourselves. Commercial wearables, while successful commercially, are not aimed at the academic environment. They have proprietary protocols, do not willingly share recorded data or information on how it was processed and filtered, and usually do not have the right sensor or actuator combinations in the right positions for the experiments we would like to run. Given the scarce resources that academic groups have, their wearables have rarely progressed past a very bulky prototype stage. But with the maker revolution, it is now possible to create a complete custom wearable within a month at very low cost (for instance, $200 for 10 prototypes).
This tutorial aims to teach the necessary skills to design and fabricate a Bluetooth based wrist or ring wearable that can wirelessly send sensor data to a smartphone or computer for data analysis and receive wireless commands to actuate sensors. Given the basic schematics for a circuit, you will learn how to choose and source components, lay out and route a circuit board, send the design off to a local fabrication house, and create the finished device when the PCBs return a week later. I will introduce helpful open source software, teach basic industry standards and the properties of various sensors and actuators, and present features that are especially useful for wearables, such as power management, battery recharging, and miniaturization techniques. The tutorial will be accompanied by full worked examples, a list of web resources and software, and the opportunity to test a working affective sensor ring constructed by the author.
Affective and gameful interfaces
Kostas Karpouzis (Institute of Communication and Computer Systems)
Dr. Kostas Karpouzis is a research director at the Institute of Communication and Computer Systems (ICCS) in Athens, Greece. His research interests lie in the areas of human computer interaction, emotion understanding, affective and adaptive interaction, serious games, and games based assessment and learning. Dr. Karpouzis is a member of the editorial board of the Journal of Multimodal User Interfaces, the Journal of Personal and Ubiquitous Computing, and the Journal of Synthetic Emotions. He recently co-edited the book 'Emotion in Games' (Springer Publishers) and he is a contributor to the 'Humaine Handbook on Emotion research' and K. Scherer's 'Blueprint for Affective Computing: a Sourcebook'. Since 1995 he has participated in more than twenty related research projects at Greek and European level; most notably the Humaine Network of Excellence, where he completed his post-doc in the field of mapping signals to signs of emotion, and the FP7 TeL Siren project (Technical Manager), which was voted Best Learning Game in Europe for 2013 by the Games and Learning Alliance Network of Excellence.
The advent of ubiquitous and wearable sensors and computing power and, especially, natural interfaces in the form of speech-based commands or hand-held devices enables users to interact with computers, gaming consoles, and portable devices in a human-like fashion, surpassing the conventional paradigm of keyboards, mice and hand-held controllers. This emerging paradigm opens up new means of non-verbal communication: users can shrug their shoulders to indicate indifference to the options presented to them, nod when agreeing or shout when angry, thus producing feedback which computing systems can take advantage of to provide a truly natural and personalized experience. In addition to this, both seasoned gamers and casual users can interact with computer and console games in the same manner as they would when playing a conventional physical or mental game.
This tutorial aims to introduce games not as a leisure or entertainment activity, but as a means to educate children and adults. Natural interaction and expressivity, personalization (starting from the user interface, all the way down to producing individual content based on what players enjoy), along with accessible computing and aesthetic emotions constitute concepts which can benefit from studying user behaviour and expressivity when playing games.