Recommender Systems use implicit and explicit user feedback to recommend desired products or items online. When the recommendation item is a task or behavior change activity, several variables, such as the difficulty of the task and users' ability to achieve it, in addition to user preferences and needs, determine the suitability of the recommendations. This paper focuses on how user ability and task difficulty concepts can be integrated into the recommendation process to personalize health activity recommendations. To this end, we compare five approaches, some borrowed from the sports and gaming world, and explore their application, advantages, and drawbacks. Through a study of two weeks, we obtained a suitable dataset to investigate how these algorithms can be used for a health recommender system (HRS) and which one is the most appropriate choice for an online HRS in terms of characteristics and flexibility required for behavior change related tailoring. We compared this choice with a baseline algorithm as part of a fully functional HRS to assess the feasibility and impact of integrating the user ability and required effort concepts on the user engagement with the recommendations in an online longitudinal study of two weeks. The results overall suggest that such integration is effective, and in addition to realizing health behavior change requirements, it improves user engagement with the recommendations. @en

Adaptive and personalized systems have become pervasive technologies that are gradually playing an increasingly important role in our daily lives. Indeed, we are now used to interact every day with algorithms that help us in several scenarios, ranging from services that suggest us music to be listened to or movies to be watched, to personal assistants able to proactively support us in complex decision-making tasks. As the importance of such technologies in our everyday lives grows, it is fundamental that the internal mechanisms that guide these algorithms are as clear as possible. Unfortunately, the current research tends to go in the opposite direction, since most of the approaches try to maximize the effectiveness of the personalization strategy (e.g., recommendation accuracy) at the expense of the explainability and the transparency of the model. The main research questions which arise from this scenario is simple and straightforward: How can we deal with such a dichotomy between the need for effective adaptive systems and the right to transparency and interpretability? The workshop aims to provide a forum for discussing such problems, challenges, and innovative research approaches in the area, by investigating the role of transparency and explainability on the recent methodologies for building user models or developing personalized and adaptive systems.

@en

Behavior change for health promotion is a complex process that requires a high level of personalization, which health recommender systems, as an emerging area, have been trying to address. Despite the advantages of behavior change theories in explaining individuals' behavior and standardizing the behavior change program overall, these theoretical models are either overlooked or unreported for the most part in health promotion systems, a small share of them being related to mental well-being. For a health recommender system to personalize interventions, the interventions should be properly designed, and the behavior change aspects should be adequately integrated into the recommendation process. This paper demonstrates an implementation guideline derived from a practical approach in integrating behavior change theories and persuasive design principles into an example mobile-based health recommender system for mental health promotion. This implementation maps a set of relevant theories for designing the health recommender system into a set of requirements using a functional framework. By realizing these requirements, one can assure that the behavior change theories are at the very least considered. This effort serves as a guideline for future implementations and highlights elements that could perhaps be used for other health or recommendation domains and, particularly, user integration purposes.@en

With the growth of interactive text or voice-enabled systems, such as intelligent personal assistants and chatbots, it is now possible to easily measure a user's mood using a conversation-based interaction instead of traditional questionnaires. However, it is still unclear if such mood measurements would be valid, akin to traditional measures, and user-engaging. Using smartphones, we compare in this paper two of the most popular traditional measures of mood: International PANAS-Short Form (I-PANAS-SF) and Affect Grid. For each of these measures, we then investigate the validity of mood measurement with a modified, chatbot-based user interface design. Our preliminary results suggest that some mood measures may not be resilient to modifications and that their alteration could lead to invalid, if not meaningless results. This exploratory paper then presents and discusses four voice-based mood tracker designs and summarizes user perception of and satisfaction with these tools.@en

Commonly used mood measures are either lengthy or too complicated for repeated use. Mood tracking research is, therefore, associated with challenges such as user dissatisfaction, fatigue, or dropouts from studies. Previous efforts to improve user experience are mostly ambiguous concerning their validity and the extent of improvement they provide (e.g., compared to established measures, such as PANAS). This paper investigates the shortening of a self-reported mood measure using smartphones with four independent samples, and provides a baseline for comparing the usability and accuracy of future measures. It first examines whether user self-assessment of overall positive and negative activations with a two-item measure can capture mood as well as I-PANAS-SF. It next examines user's learning effect in repeated usage of the measure. Finally, it introduces the design of an adaptive mood measure that reduces the number of questions based on its prediction of user mood fluctuations. This adaptive measure can potentially capture specific mood states, as well as overall mood. The paper then explores user satisfaction and compliance with this measure in a longitudinal study. The results of this paper reveal that the investigated two-item measure is a valid and reliable tool for capturing a user's overall mood and mood fluctuations. The negative activation from this measure is associated with stress. Our results suggest that the association between mood and stress generally depends on the measure of mood and its items. We discovered that a non-complex self-explanatory measure is fairly resilient for repeated use with respect to the required effort and the accuracy of the measure in both daily and weekly evaluations. Adaptively reducing the length of a mood measure does not seem to impact user compliance but may slightly improve usability. We also noticed that positive and negative activations have a slightly different pattern of behavior with reference to the preceding mood states.@en

Adaptive and personalized systems have become pervasive technologies which are gradually playing an increasingly important role in our daily lives. Indeed, we are now used to interact every day with algorithms that help us in several scenarios, ranging from services that suggest us music to be listened to or movies to be watched, to personal assistants able to proactively support us in complex decision-making tasks. As the importance of such technologies in our everyday lives grows, it is fundamental that the internal mechanisms that guide these algorithms are as clear as possible. Unfortunately, the current research tends to go in the opposite direction, since most of the approaches try to maximize the effectiveness of the personalization strategy (e.g., recommendation accuracy) at the expense of the explainability and the transparency of the model. The main research questions which arise from this scenario is simple and straightforward: How can we deal with such a dichotomy between the need for effective adaptive systems and the right to transparency and interpretability? The workshop aims to provide a forum for discussing such problems, challenges and innovative research approaches in the area, by investigating the role of transparency and explainability on the recent methodologies for building user models or for developing personalized and adaptive systems.@en

In recent years, recommender systems have emerged as a key component for personalization in health applications. Central in the development of recommender systems is rating-based preference elicitation, based both on single-criterion and multi-criteria rating. Though its use has already been studied in various domains of recommender systems, far too little attention has been paid to preference elicitation in health recommender systems~(HRS). The purpose of this paper is to develop a better understanding of this preference elicitation by studying the criteria that users consider when they rate a health promotion recommendation from HRS, and accordingly, to offer a design solution as a functional feedback model for mobile health applications. This paper investigates the user-perceived importance of various criteria, as well as latent factors for eliciting user feedback on the recommendations. It also reports the relationship of explanation and trust to the overall rating. By aggregating a list of all possible criteria, we further discover that not all criteria are equally important to users, and that the effectiveness of a recommendation plays a dominant role.@en

Recommender systems (RS) often use implicit user preferences extracted from behavioral and contextual data, in addition to traditional rating-based preference elicitation, to increase the quality and accuracy of personalized recommendations. However, these approaches may harm user experience by causing mixed emotions, such as fear, anxiety, surprise, discomfort, or creepiness. RS should consider users' feelings, expectations, and reactions that result from being shown personalized recommendations. This paper investigates the creepiness of recommendations using an online experiment in three domains: movies, hotels, and health. We defne the feeling of creepiness caused by recommendations and fnd out that it is already known to users of RS. We further fnd out that the perception of creepiness varies across domains and depends on recommendation features, like causal ambiguity and accuracy. By uncovering possible consequences of creepy recommendations, we also learn that creepiness can have a negative infuence on brand and platform attitudes, purchase or consumption intention, user experience, and users' expectations of-and their trust in-RS.

@en

A multi-criteria rating looks for important dimensions to more extensively capture an individual’s opinion about a recommended item. Health Recommender Systems (HRS) is considered to be an emerging domain of recommender systems. In HRS, criteria for a multi-criteria preference elicitation of a recommendation have not yet been fully investigated to the best of our knowledge. In this paper, we investigate the criteria for the rating of a health promotion recommendation using an online survey. Drawing on both the relevant literature and the users’ responses, we came up with a list of 33 criteria that users are considering when they rate a health promotion recommendation. However, these criteria are not equally important to users. We discuss which of these criteria are more important in the users’ opinions. In short, our results show that users consistently consider effectiveness, emotional gain, and giving a good feeling as the most important criteria. Using the criteria derived from the literature, we came up with a model for the importance of the criteria which has three dimensions: effect, effort, and context. This study is the first step toward enhancing our understanding of HRS and the rating of a health promotion recommendation.@en

A growing number of studies in the computer science and engineering communities are addressing mood, an affective phenomenon related but not equivalent to emotion. While emotion has been investigated intensely in the affective computing domain, the characteristics and applications of mood are relatively unexplored. Through a bottom-up approach, this paper aims to identify in which areas and for what purposes computer scientists and other researchers in the ACM and IEEE communities are studying mood. Based on a literature review of 1,264 peer-reviewed publications, this paper proposes a taxonomy of mood research in affective computing. Despite a wide range of applications and domains, core themes of mood research relate to identifying users' mood, influencing it, or helping users to communicate their mood to others. The conceptualization and definition of mood, however, vary between the studies surveyed and sometimes can fall considerably far from the psychological concept of mood in affect research. In several instances, researchers use the terms mood and emotion interchangeably and do not sufficiently discuss the implications both for their measurements and for the design of affective-computing systems as well. With our study, we aim to contribute a clearer conceptualization of mood research and to provide researchers with a broad overview of the research as well as areas of applications in which mood is addressed.@en