1,720,998 research outputs found
Recommender Systems: Between Acceptance and Refusal
No full textRecommender Systems (RSs) are a prominent solution to the problem of information overload on the web. It is impossible for users to process or even understand all information presented to them. Also, it becomes more and more difficult for an individual to identify appropriate concrete pieces of information or information sources. RSs aim at adapting the presented content and the order in which it is presented to users’ individual needs, based on their preferences and past behavior. Yet, a system can only provide accurate recommendations if it has been authentically used before, i.e., been able to collect information about a user. As authentic usage depends on a user’s acceptance, the success of RSs in general is strongly dependent on acceptance also. If recommendations seem inappropriate, the trust in the system will fade. This paper presents a study analyzing how and to what extent different factors like transparency or controllability influence acceptance in the context of web-based recommendation
Adaptive User Interfaces on Tablets to Support People With Disabilities
No full textWith the advent of tablet computers, touch screens, gesture-based interaction and speech recognition, sophisticated applications with Natural User Interfaces (NUIs) become state of the art. NUIs have the potential to support people with disabilities, e.g., in their daily activities or in acquiring specific skills. Yet, one main challenge is that this user group has diverse abilities and handicaps so that an interaction design must be highly configurable to make NUIs beneficial. The introduction of adaptivity might be promising in order to overcome configuration complexity and effort. This paper presents an approach to adaptive user interfaces on tablets to support people with disabilities
9. User awareness in music recommender systems
No full textMusic recommender systems are a widely adopted application of personalized systems and interfaces. By tracking the listening activity of their users and building preference profiles, a user can be given recommendations based on the preference profiles of all users (collaborative filtering), characteristics of the music listened to (content-based methods), meta-data and relational data (knowledge-based methods; sometimes also considered content-based methods), or a mixture of these with other features (hybrid methods). In this chapter, we focus on the listener´s aspects of music recommender systems. We discuss different factors influencing relevance for recommendation on both the listener´s and the music´s side and categorize existing work. In more detail, we then review aspects of (i) listener background in terms of individual, i. e., personality traits and demographic characteristics, and cultural features, i. e., societal and environmental characteristics, (ii) listener context, in particular modeling dynamic properties and situational listening behavior, and (iii) listener intention, in particular by studying music information behavior, i. e., how people seek, find, and use music information. This is followed by a discussion of user-centric evaluation strategies for music recommender systems. We conclude the chapter with a reflection on current barriers, by pointing out current and longer-term limitations of existing approaches and outlining strategies for overcoming these
Integrating semantic relatedness in a collaborative filtering system
No full textCollaborative Filtering (CF) recommender systems use opinions of people for filtering relevant information. The accuracy of these applications depends on the mechanism used to filter and combine the opinions (the feedback) provided by users. In this paper we propose a mechanism aimed at using semantic relations extracted from Wikipedia in order to adaptively filter and combine the feedback of people. The semantic relatedness among the concepts/pages of Wikipedia is used to identify the opinions which are more significant for predicting a rating for an item. We show that our approach improves the accuracy of the predictions and it also opens opportunities for providing explanations on the obtained recommendations
Influencing Factors for User Context in Proactive Mobile Recommenders
No full textProactive recommender systems break the standard request-response pattern of traditional recommenders by pushing item suggestions to the user when the situation seems appropriate. To support proactive recommendations in a mobile scenario, we have developed a two-phase proactivity model based on the current context of the user. In this paper, we explain our approach to model context by identifying different components: user and device status, and user activity. We have conducted an online survey among over 100 users to investigate how different context attributes influence the decision when to generate proactive recommendations. Thus, we were able to acquire appropriateness factors and weights for the context features in our proactivity model
Theory-grounded user modeling for personalized HCI
No full textPersonalized systems are systems that adapt themselves to meet the inferred needs of individual users. The majority of personalized systems mainly rely on data describing how users interacted with these systems. A common approach is to use historical data to predict users' future needs, preferences, and behavior to subsequently adapt the system to these predictions. However, this adaptation is often done without leveraging the theoretical understanding between behavior and user traits that can be used to characterize individual users or the relationship between user traits and needs that can be used to adapt the system. Adopting a more theoretical perspective can benefit personalization in two ways: (i) letting systems rely on theory can reduce the need for extensive data-driven analysis, and (ii) interpreting the outcomes of data-driven analysis (such as predictive models) from a theoretical perspective can expand our knowledge about users. However, incorporating theoretical knowledge in personalization brings forth a number of challenges. In this chapter, we review literature that taps into aspects of (i) psychological models from traditional psychological theory that can be used in personalization, (ii) relationships between psychological models and online behavior, (iii) automated inference of psychological models from data, and (iv) how to incorporate psychological models in personalized systems. Finally, we propose a step-by-step approach on how to design personalized systems that take user traits into account.</p
MERCURY: User Centric Device and Service Processing – Demo paper
No full textIn this paper, we present MERCURY, a platform for simple, user-centric integration and management of heterogeneous devices and services via a web-based interface. In contrast to existing approaches, MERCURY is geared towards non-IT-savvy end users. It enables these end users to easily interconnect devices, which can act as sensors or actuators, to model rules that trigger actions. Sets of rules allow users to model entire, often reoccurring, scenarios. Also, these must be user-centric and context adaptive. It shall thus enable users to take full advantage of the potential for support in everyday life such integration offers. Technically, our solution is based on Portal technology. We describe a tangible scenario to portray the steps a user will need to take to achieve the desired functionality
Mining Twitter for Cultural Patterns
No full textAdaptive applications rely on the knowledge of their users, their needs and differences. For instance, in the scope of the ImReal 1 project, a training process is adapted to users’ origins using information on user cultural backgrounds. For inferring culture-specific information from available microblogging content, we monitor the usage of Twitter elements such as hashtags, web links and user mentions. We analyze how users from different cultural groups employ these elements when they tweet. This allows us to get insights on microblogging patterns for different cultural groups of Twitter users and an outlook into user preferences and traits towards sharing content with others, time preferences, and social networking attitudes. Potentially, such information can be used for adapting software applications in accord with user culture-specific behavioral traits
- …
