Real World User Model: Evolution of User Modeling Triggered by Advances in Wearable and Ubiquitous Computing

Abstract

Over the last few years, user modeling scenery is changing. With the recent advancements in ubiquitous and wearables technologies, the amount and type of data that can be gathered about users and used to build user models is expanding. User Model can now be enriched with data regarding different aspects of people's everyday lives. All these changes bring forth new research questions about the kinds of services which could be provided, the ways for effectively conveying new forms of personalisation and recommendation, and how traditional user modeling should change to exploit ubiquitous and wearable technology to provide these services. In this paper we follow the evolution of user modeling process, starting from the traditional User Model and progressing to RWUM -Real World User Model, which contains data from a person's everyday life. We tried to answer the above questions and to present a conceptual framework that represents the RWUM process, which might be used as a reference model for designing RWUM-based systems. Finally, we propose some inspiring usage scenarios and design directions that can guide researchers in designing novel, robust and versatile services based on RWUM.

Exploring the Effects of Natural Language Justifications in Food Recommender Systems

“…The Profiler module initiates the process to obtain information on a user. It implements a profiling strategy based on the holistic user modeling paradigm [5][6][7]34], which has already been used in previous studies concerning food recommendations [35]. Table 1 outlines the seven user aspects used, which are encoded in each user profile: demographics, preferences, goals, affect, behavioral data, health data, and domain-related information.…”

Generating Recommendations From Multiple Data Sources: A Methodological Framework for System Design and Its Application

“…This said, a main contribution of this paper is related to explain how to effectively exploit a HUM for recommendation purposes, by pointing out all those passages that need to be considered for designing holistic recommender systems. More concretely, HUMs are inspired by the model proposed by Cena et al in [11], where real-word data coming from environmental and wearable sensors are used to model the user. With respect of such conceptualization, HUM also includes information coming from the web (social connections, interactions, textual messages like posts, comments and tags) in order to create a more complete picture of the user.…”

“…By following these insights, in this article we introduce the concept of Holistic Recommendation (RecHol in the following), that is to say, a suggestion that is obtained by considering a comprehensive representation of the user, as well as of the recommendation task itself. To model the user we exploited what we called holistic user profiles, extensive user models that encode in a single user profile information about the user's interests, affects, psychological states, physical states, social connections and behaviors [11], [29]. Such a representation is obtained by gathering rough data from diverse data sources, such as social networks, smartphones, wearable devices, and environment sensors, and by reasoning over these data in order to populate the different facets of the profile.…”

Preface to the special issue on harnessing personal tracking data for personalization and sense-making

“…Thinking of further challenges, we argue that user models can now be expanded to make use of a variety of information that could be used to model the user's attitudes, emotions, tastes, physiology, movements, everyday behaviors, habits, working and learning performances, media uses, and preferences (Cena et al 2019). Such information may create rich "QS user models", i.e., users models based on personal tracking data.…”