The Learning Companion Application was actually designed to fit the needs of master craftsmen in a blended learning Energy Consultant Training at the chamber of crafts. It supports mobile learning particularly through its responsive design and recommendation engine. However, its design follows the recommended practice taught in a university course for master students about Advanced Web Technologies. That is why we introduced the same application for this computer science course to provide students with a contextual and situated learning experience: students learn with the help of a system that implements many concepts they have to learn. Topics, such as HTML5, the development of responsive web applications and recommender systems, are introduced in the lecture and can be experienced as real world examples by the students in the learning app as well. Similar to common learning management systems, our Learning Companion Application offers the lecture materials as digital media assets, such as texts, source code, animations or videos. In addition, the application tracks the interactions of the students in order to give overviews of the learners' knowledge levels on the different learning objects at every time, in order to identify learning weaknesses to improve teaching with the help of a learning analytics module. It can recommend appropriate learning objects which fit the predicted knowledge and the current situation of the learner, e.g. available time for learning. This paper presents taught concepts in the lecture and their implementation in the Learning Companion Application as well as a study of the interaction and learning behavior of the computer science students.

The FI-CONTENT project aims at establishing the foundation of a European infrastructure for developing and testing novel smart city services. The Smart City Services Platform will develop enabling technology for SMEs and developer to create services offering residents and visitors to cities smart services that enhance their city visit or daily life. We have made use of generic, specific and common enablers to develop a reference implementation, the Smart City Guide web app. The basic information is provided by the Open City Database, an open source specific enabler that can be used for any city in Europe. Recommendation as a Service is an enabler that can be applied to lots use cases, here we describe how we integrated it into the Smart City Guide. The uses cases will be iteratively improved and upgraded during regular iterative cycles based on feedback gained in lab and field trials at the experimentation sites. As the app is transferable to any city, it will be tested at a number of experimentation sites.

Some of the known issues of recommendation algorithms are a result of the so called "Cold Start Problem" that is caused by a lack of sufficient data of users, items or the content, which are essential for the calculation of context-sensitive predictions. Along with this comes the "Sparsity Problem" which also exposes the problem of recommendation systems which are being provided with too little information of user feedback such as likes and views. As a consequent collaborative and knowledgebased filtering algorithms are unable of precise prediction which is causing a decline of the customer satisfaction. If beyond that there also is a lack of metadata, the calculation of similarities through content-based filtering algorithms is likely to fail as well.This paper introduces preference ontologies and how they help to reduce these issues by analyzing external data, in terms of texts from social networks and other web sources. Thereby we introduce a self-designed semantic engine, performing sentiment analysis and semantic keyword extraction. These novel ontologies represent the mined information and thus, describe the users interest in automatic analyzed topics and map them to the meta data of items in recommendation engines.

No abstract

Recommendation systems leverage future internet services to predict personalized recommendations for products, services, media entities or other offerings. Based on the research and development of the FIcontent 2 initiative, we introduce an approach to compensate Cold Start and Sparsity Problems by analyzing semantics of external textual data, in terms of comments from social networks as well as item reviews from product and rating services. Thereby sentiment analysis and semantic keyword extraction approaches are explained and evaluated by using preliminary implementations. The mined data is transferred into, so called, preference ontologies describing the users interest in automatic analyzed topics and subsequently mapped to the properties of items in order to calculate the associated recommendation value.