This paper presents a proof of concept from which the metaphor of “fair trade” is validated as an alternative to manage the private information of users. Our privacy solution deals with user’s privacy as a tradable good for obtaining environmental services. Thus, users gain access to more valuable services as they share more personal information. This strategy, combined with optimistic access control and transaction registry mechanisms, enhances users’ confidence in the system while encouraging them to share their information, with the consequent benefit for the community. The study results are promising considering the user responses regarding the usefulness, ease of use, information classification and perception of control with the mechanisms proposed by the metaphor.
In the educational context there is an increasing interest in learning networks. Recommendation systems can play an important role in achieving the educational objectives. Although we can find many papers focused on recommendation techniques and algorithms however, less attention has been dedicated to social factors that influence the recommendation process. This process could be improved if we had a deeper understanding of the social factors that influence the quality or goodness of a suggestion made by the recommendation system. This work elucidates and analyses the social factors that influence the design and decision making process of recommender systems. We conducted a survey where 126 undergraduate students were asked to extract are the main factors for improving suggestions when they are interacting with an Online Social Network (OSN) or in an Educational Social Network (ESN). The results show that different factors have to be considered depending on the type of the network.
Pablo A. Haya, Oliver Daems, Nils Malzahn, Jorge Castellanos and Heinz Ulrich Hoppe
British Journal of Educational Technology. Article first published online: 3 MAR 2015 (2015) DOI: 10.1111/bjet.12264 [download] (JCR, IF 2014: 1.394, Q1)
Learning Analytics constitutes a key tool for supporting Learning Design and teacher-led inquiry into student learning. In this paper, we demonstrate how a Social Learning Analytics toolkit can combine social network analysis and content analysis for supporting a global and formal teacher inquiry. This toolkit not only supports teachers in improving the organisation of the learning process but also generates important input to improve the students’ reflection on their own learning. Our examples show how combinations of different levels of analysis can provide deep insight in the learning process. We report a case study that exemplifies the main features of our approach and the kind of outcomes that can be obtained. Commenting and rating processes on videos are analysed based on user traces from a social learning platform. Finally, we point out implications on the learning design for networked learning environments in general.
David Aguado, Pablo A. Haya, Alvaro Barbero
Los gestores de RR.HH. han declarado explícitamente su interés por el Big Data. A pesar de ello, a día de hoy, no es fácil encontrar en nuestro país proyectos de Big Data ejecutados en el negocio de la gestión de Recursos Humanos. Este artículo pretende ayudar al gestor de RR.HH. a entender qué es el Big Data y cómo puede ponerlo al servicio de su negocio, ofreciéndole una visión específica de cómo se define y cuáles son sus características principales, las aplicaciones desarrolladas hasta la fecha en este sector y las dificultades y retos principales a la hora de implantar modelos Big Data en la gestión de Recursos Humanos.
Leila S. Shafti, Pablo A. Haya, Manuel García-Herranz, Eduardo Pérez
Journal of Ambient Intelligence and Smart Environments 5 (6), 563-587 (2013) [download] (JCR, IF 2012: 1.298, Q2)
One of the goals in Ambient Intelligence is to enable Intelligent Environments to take decisions based on the perceived context. In our previous work, we successfully explored how the inhabitants can communicate their own preferences with the environment using Event-Condition-Action (ECA) rules. The easiness of the communication language combined with an appropriate explanation mechanism gives trust to the Intelligent Environment actions. However, defining every preference, and maintaining them up-to-date can be cumbersome. Therefore, a complementary mechanism is required to learn from user behavior and adapt to small changes without being explicitly requested for. Inferring behaviors effectively from data collected from sensors in an Intelligent Environment is a challenging problem. The main issues include primitive representation of data, the necessity of a high number of sensors, and dealing with few training data collected in a short time. We present MFE3/GADR, an evolutionary constructive induction method to ease inferring inhabitants’ preferences from data collected from simple sensors. We show that this method detects successfully relevant sensors and constructs highly informative features that abstract relations among them. The constructed features, in addition to improving significantly the learning accuracy, break down and encapsulate the performance of inhabitants into decision trees that can easily be converted to ECA rules for further use in the Intelligent Environment. Comparing the empirical results show that our method can reduce a large set of complex ECA rules that represent the preferences to a smaller set of simple ECA rules.
P. Molins-Ruano, C. Sevilla, S. Santini, P.A. Haya, P. Rodríguez, G.M. Sacha
The use of new technical tools as a mean to increase the motivation and improve the education of students is an intriguing and pressing issue. Specifically, great interest has been shown in the use of videogames since they constitute a common leisure-time activity of many young students, a circumstance that shows their motivational, if not their educational, potential. In this paper we suggest that the design of videogames can be a very effective activity. To demonstrate this, we have used game design as a test-bed for an experience involving Computer Science and History students: interdisciplinary teams have cooperated in the design of a video-game on an historical theme. The experience has been repeated along three academic years. The students’ motivation has been evaluated in the last 2 years, demonstrating that it is higher when they use the interdisciplinary design of videogames as a way of learning instead of traditional learning methods.
User Modeling and Adaptation for Daily Routines
Providing Assistance to People with Special Needs
Editors: Estefanía Martín, Pablo A. Haya, Rosa M. Carro
ISBN: 978-1-4471-4777-0 (Print) 978-1-4471-4778-7 (Online)
User Modeling and Adaptation for Daily Routines is motivated by the need to bring attention to how people with special needs can benefit from adaptive methods and techniques in their everyday lives. Assistive technologies, adaptive systems and context-aware applications are three well-established research fields. There is, in fact, a vast amount of literature that covers HCI-related issues in each area separately. However, the contributions in the intersection of these areas have been less visible, despite the fact that such synergies may have a great impact on improving daily living.
Presenting a comprehensive review of state-of-the-art practices on user modeling and adaptation for people with special needs, as well as some reflections on the challenges that need to be addressed in this direction, topics covered within this volume include the analysis, design, implementation and evaluation of adaptive systems to assist users with special needs to take decisions and fulfil daily routine activities. Particular emphasis is paid to major trends in user modeling, ubiquitous adaptive support, diagnostic and accessibility, recommender systems, social interaction, designing and building adaptive assistants for daily routines, field studies and automated evaluation.
Nine leading contributors write on key current research in the domain of adaptive applications for people with special needs, integrating and summarizing findings from the best known international research groups in these areas. User Modeling and Adaptation for Daily Routines highlights how adaptation technologies can ease daily living for all, and support sustainable high-quality healthcare, demographic ageing and social/economic inclusion.