Launched in 2016, the Health Recommender Systems Workshop (HealthRecSys) rapidly became a central forum for discussing the transformative capabilities of personalized recommender systems within the health and care sectors. Despite the unforeseen pause due to the COVID-19 pandemic and other challenges, the workshop’s influence persisted through its vibrant community and publications. Our aim with the 6th HealthRecSys is to reignite these conversations and provide a forward-thinking platform that revisits the foundational elements that have contributed to the field’s growth. However, the workshop aspires to do more by infusing new perspectives and tackling the most pressing global challenges and technological innovations head-on with contemporary themes such as the impact of global health crises, generative AI models, personalized and self-managed care, and the increasing focus on health equity. HealthRecSys is dedicated to strengthening the network of researchers working on health recommender systems, drawing participants from an array of health and care domains. Through our combined interactive and paper based workshop format, we aim at cultivating a cross-disciplinary community that promotes collaboration among recommender systems specialists, healthcare professionals, ethicists, and policymakers, among others.

Popularity bias is a prominent phenomenon in recommender systems (RS), especially in the music domain. Although popularity bias mitigation techniques are known to enhance the fairness of RS while maintaining their high performance, there is a lack of understanding regarding users’ actual perception of the suggested music. To address this gap, we conducted a user study (n=40) exploring user satisfaction and perception of personalized music recommendations generated by algorithms that explicitly mitigate popularity bias. Specifically, we investigate item-centered and user-centered bias mitigation techniques, aiming to ensure fairness for artists or users, respectively. Results show that neither mitigation technique harms the users’ satisfaction with the recommendation lists despite promoting underrepresented items. However, the item-centered mitigation technique impacts user perception; by promoting less popular items, it reduces users’ familiarity with the items. Lower familiarity evokes discovery—the feeling that the recommendations enrich the user’s taste. We demonstrate that this can ultimately lead to higher satisfaction, highlighting the potential of less-popular recommendations to improve the user experience.

Universities have increasingly diverse student populations. While a greater variety of students' backgrounds, skills and abilities exist, this does not necessarily mean they have more inclusive interactions. A lack of inclusive interactions can cause negative biases against people who are different from oneself. One strategy to mitigate bias is exposure to situations where students encounter social dilemmas with others and are stimulated to reflect on their interactions. These experiences could be simulated within a serious game as a safe learning environment. Moreover, serious games allow the player to broaden their mental perspective by showing the world through the eyes of others. This paper presents the design and evaluation of the serious game called Diverse Perspectives. This visual novel with multiple endings captures social dilemmas and allows the player to view them from a different angle through perspective switches. We evaluate Diverse Perspectives with quantitative ( N = 32) and qualitative measures on attitude towards diversity and gaming experience measured with the Shortened Version of the Miville-Guzman Universality-Diversity Scale and the Game Experience Questionnaire. Participants indicate they find the perspective switch helpful as it creates an understanding of the other person's view.

Language models are widely used for different Natural Language Processing tasks while suffering from a lack of personalization. Personalization can be achieved by, e.g., fine-tuning the model on training data that is created by the user (e.g., social media posts). Previous work shows that the acquisition of such data can be challenging. Instead of adapting the model's parameters, we thus suggest selecting a model that matches the user's mental model of different thematic concepts in language. In this article, we attempt to capture such individual language understanding of users. In this process, two challenges have to be considered. First, we need to counteract disengagement since the task of communicating one's language understanding typically encompasses repetitive and time-consuming actions. Second, we need to enable users to externalize their mental models in different contexts, considering that language use changes depending on the environment. In this article, we integrate methods of gamification into a visual analytics (VA) workflow to engage users in sharing their knowledge within various contexts. In particular, we contribute the design of a gameful VA playground called Concept Universe. During the four-phased game, the users build personalized concept descriptions by explaining given concept names through representative keywords. Based on their performance, the system reacts with constant visual, verbal, and auditory feedback. We evaluate the system in a user study with six participants, showing that users are engaged and provide more specific input when facing a virtual opponent. We use the generated concepts to make personalized language model suggestions.

A common criteria for Explainable AI (XAI) is to support users in establishing appropriate trust in the AI – rejecting advice when it is incorrect, and accepting advice when it is correct. Previous findings suggest that explanations can cause an over-reliance on AI (overly accepting advice). Explanations that evoke appropriate trust are even more challenging for decision-making tasks that are difficult for humans and AI. For this reason, we study decision-making by non-experts in the high-uncertainty domain of stock trading. We compare the effectiveness of three different explanation styles (influenced by inductive, abductive, and deductive reasoning) and the role of AI confidence in terms of a) the users’ reliance on the XAI interface elements (charts with indicators, AI prediction, explanation), b) the correctness of the decision (task performance), and c) the agreement with the AI’s prediction. In contrast to previous work, we look at interactions between different aspects of decision-making, including AI correctness, and the combined effects of AI confidence and explanations styles. Our results show that specific explanation styles (abductive and deductive) improve the user’s task performance in the case of high AI confidence compared to inductive explanations. In other words, these styles of explanations were able to invoke correct decisions (for both positive and negative decisions) when the system was certain. In such a condition, the agreement between the user’s decision and the AI prediction confirms this finding, highlighting a significant agreement increase when the AI is correct. This suggests that both explanation styles are suitable for evoking appropriate trust in a confident AI.

Existing eXplainable Artificial Intelligence (XAI) techniques support people in interpreting AI advice. However, although previous work evaluates the users’ understanding of explanations, factors influencing the decision support are largely overlooked in the literature. This article addresses this gap by studying the impact of user uncertainty , AI correctness , and the interaction between AI uncertainty and explanation logic-styles for classification tasks. We conducted two separate studies: one requesting participants to recognize handwritten digits and one to classify the sentiment of reviews. To assess the decision making, we analyzed the task performance, agreement with the AI suggestion, and the user’s reliance on the XAI interface elements. Participants make their decision relying on three pieces of information in the XAI interface (image or text instance, AI prediction, and explanation). Participants were shown one explanation style (between-participants design) according to three styles of logical reasoning (inductive, deductive, and abductive). This allowed us to study how different levels of AI uncertainty influence the effectiveness of different explanation styles. The results show that user uncertainty and AI correctness on predictions significantly affected users’ classification decisions considering the analyzed metrics. In both domains (images and text), users relied mainly on the instance to decide. Users were usually overconfident about their choices, and this evidence was more pronounced for text. Furthermore, the inductive style explanations led to overreliance on the AI advice in both domains—it was the most persuasive, even when the AI was incorrect. The abductive and deductive styles have complex effects depending on the domain and the AI uncertainty levels.

We present an approach that shows all relevant subspaces of categorical data condensed in a single picture. We model the categorical values of the attributes as co-occurrences with data partitions generated from structured data using pattern mining. We show that these co-occurrences are a-priori , allowing us to greatly reduce the search space, effectively generating the condensed picture where conventional approaches filter out several subspaces as these are deemed insignificant. The task of identifying interesting subspaces is common but difficult due to exponential search spaces and the curse of dimensionality. One application of such a task might be identifying a cohort of patients defined by attributes such as gender, age, and diabetes type that share a common patient history, which is modeled as event sequences. Filtering the data by these attributes is common but cumbersome and often does not allow a comparison of subspaces. We contribute a powerful multi-dimensional pattern exploration approach (MDPE-approach) agnostic to the structured data type that models multiple attributes and their characteristics as co-occurrences, allowing the user to identify and compare thousands of subspaces of interest in a single picture. In our MDPE-approach, we introduce two methods to dramatically reduce the search space, outputting only the boundaries of the search space in the form of two tables. We implement the MDPE-approach in an interactive visual interface (MDPE-vis) that provides a scalable, pixel-based visualization design allowing the identification, comparison, and sense-making of subspaces in structured data. Our case studies using a gold-standard dataset and external domain experts confirm our approach’s and implementation’s applicability. A third use case sheds light on the scalability of our approach and a user study with 15 participants underlines its usefulness and power.

Abstract Music analysis tasks, such as structure identification and modulation detection, are tedious when performed manually due to the complexity of the common music notation (CMN). Fully automated analysis instead misses human intuition about relevance. Existing approaches use abstract data‐driven visualizations to assist music analysis but lack a suitable connection to the CMN. Therefore, music analysts often prefer to remain in their familiar context. Our approach enhances the traditional analysis workflow by complementing CMN with interactive visualization entities as minimally intrusive augmentations. Gradual step‐wise transitions empower analysts to retrace and comprehend the relationship between the CMN and abstract data representations. We leverage glyph‐based visualizations for harmony, rhythm and melody to demonstrate our technique's applicability. Design‐driven visual query filters enable analysts to investigate statistical and semantic patterns on various abstraction levels. We conducted pair analytics sessions with 16 participants of different proficiency levels to gather qualitative feedback about the intuitiveness, traceability and understandability of our approach. The results show that MusicVis supports music analysts in getting new insights about feature characteristics while increasing their engagement and willingness to explore.

Abstract Language models, such as BERT, construct multiple, contextualized embeddings for each word occurrence in a corpus. Understanding how the contextualization propagates through the model's layers is crucial for deciding which layers to use for a specific analysis task. Currently, most embedding spaces are explained by probing classifiers; however, some findings remain inconclusive. In this paper, we present LMFingerprints, a novel scoring‐based technique for the explanation of contextualized word embeddings. We introduce two categories of scoring functions, which measure (1) the degree of contextualization, i.e., the layerwise changes in the embedding vectors, and (2) the type of contextualization, i.e., the captured context information. We integrate these scores into an interactive explanation workspace. By combining visual and verbal elements, we provide an overview of contextualization in six popular transformer‐based language models. We evaluate hypotheses from the domain of computational linguistics, and our results not only confirm findings from related work but also reveal new aspects about the information captured in the embedding spaces. For instance, we show that while numbers are poorly contextualized, stopwords have an unexpected high contextualization in the models' upper layers, where their neighborhoods shift from similar functionality tokens to tokens that contribute to the meaning of the surrounding sentences.

Abstract Healthy nutrition contributes to preventing non-communicable and diet-related diseases. Recommender systems, as an integral part of mHealth technologies, address this task by supporting users with healthy food recommendations. However, knowledge about the effects of the long-term provision of health-aware recommendations in real-life situations is limited. This study investigates the impact of a mobile, personalized recommender system named Nutrilize. Our system offers automated personalized visual feedback and recommendations based on individual dietary behaviour, phenotype, and preferences. By using quantitative and qualitative measures of 34 participants during a study of 2–3 months, we provide a deeper understanding of how our nutrition application affects the users’ physique, nutrition behaviour, system interactions and system perception. Our results show that Nutrilize positively affects nutritional behaviour (conditional $$R^2=.342$$ R 2 = . 342 ) measured by the optimal intake of each nutrient. The analysis of different application features shows that reflective visual feedback has a more substantial impact on healthy behaviour than the recommender (conditional $$R^2=.354$$ R 2 = . 354 ). We further identify system limitations influencing this result, such as a lack of diversity, mistrust in healthiness and personalization, real-life contexts, and personal user characteristics with a qualitative analysis of semi-structured in-depth interviews. Finally, we discuss general knowledge acquired on the design of personalized mobile nutrition recommendations by identifying important factors, such as the users’ acceptance of the recommender’s taste, health, and personalization.

Rita Sevastjanova, Aikaterini-Lida Kalouli, Christin Beck, Hanna Schäfer, Mennatallah El-Assady. Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers). 2021.

Abstract Mixed‐initiative visual analytics systems support collaborative human‐machine decision‐making processes. However, many multi‐objective optimization tasks, such as topic model refinement, are highly subjective and context‐dependent. Hence, systems need to adapt their optimization suggestions throughout the interactive refinement process to provide efficient guidance. To tackle this challenge, we present a technique for learning context‐dependent user preferences and demonstrate its applicability to topic model refinement. We deploy agents with distinct associated optimization strategies that compete for the user's acceptance of their suggestions. To decide when to provide guidance, each agent maintains an intelligible, rule‐based classifier over context vectorizations that captures the development of quality metrics between distinct analysis states. By observing implicit and explicit user feedback, agents learn in which contexts to provide their specific guidance operation. An agent in topic model refinement might, for example, learn to react to declining model coherence by suggesting to split a topic. Our results confirm that the rules learned by agents capture contextual user preferences. Further, we show that the learned rules are transferable between similar datasets, avoiding common cold‐start problems and enabling a continuous refinement of agents across corpora.

Movement-compensating interactions like teleportation are commonly deployed techniques in virtual reality environments. Although practical, they tend to cause disorientation while navigating. Previous studies show the effectiveness of orientation-supporting tools, such as trails, in reducing such disorientation and reveal different strengths and weaknesses of individual tools. However, to date, there is a lack of a systematic comparison of those tools when teleportation is used as a movement-compensating technique, in particular under consideration of different tasks. In this paper, we compare the effects of three orientation-supporting tools, namely minimap, trail, and heatmap. We conducted a quantitative user study with 48 participants to investigate the accuracy and efficiency when executing four exploration and search tasks. As dependent variables, task performance, completion time, space coverage, amount of revisiting, retracing time, and memorability were measured. Overall, our results indicate that orientation-supporting tools improve task completion times and revisiting behavior. The trail and heatmap tools were particularly useful for speed-focused tasks, minimal revisiting, and space coverage. The minimap increased memorability and especially supported retracing tasks. These results suggest that virtual reality systems should provide orientation aid tailored to the specific tasks of the users.

HealthRecSys 2020 was the 5th International Workshop on Health Recommender Systems held in conjunction with the 14th ACM Conference on Recommender Systems. This workshop followed the previous workshop in 2019 [4] and focused on the application and potentials of recommender systems on health promotion, health care, and health-related topics. By engaging in the discussion and representation of health domains into recommender systems, this workshop facilitated the cross-domain collaborations and exchange of knowledge and infrastructure. This year, in particular, COVID-19-related contributions were discussed.

Abstract Domain experts for collective animal behavior analyze relationships between single animal movers and groups of animals over time and space to detect emergent group properties. A common way to interpret this type of data is to visualize it as a spatio‐temporal network. Collective behavior data sets are often large, and may hence result in dense and highly connected node‐link diagrams, resulting in issues of node‐overlap and edge clutter. In this design study, in an iterative design process, we developed glyphs as a design for seamlessly encoding relationships and movement characteristics of a single mover or clusters of movers. Based on these glyph designs, we developed a visual exploration prototype, MotionGlyphs, that supports domain experts in interactively filtering, clustering, and animating spatio‐temporal networks for collective animal behavior analysis. By means of an expert evaluation, we show how MotionGlyphs supports important tasks and analysis goals of our domain experts, and we give evidence of the usefulness for analyzing spatio‐temporal networks of collective animal behavior.

We propose a framework for interactive and explainable machine learning that enables users to (1) understand machine learning models; (2) diagnose model limitations using different explainable AI methods; as well as (3) refine and optimize the models. Our framework combines an iterative XAI pipeline with eight global monitoring and steering mechanisms, including quality monitoring, provenance tracking, model comparison, and trust building. To operationalize the framework, we present explAIner, a visual analytics system for interactive and explainable machine learning that instantiates all phases of the suggested pipeline within the commonly used TensorBoard environment. We performed a user-study with nine participants across different expertise levels to examine their perception of our workflow and to collect suggestions to fill the gap between our system and framework. The evaluation confirms that our tightly integrated system leads to an informed machine learning process while disclosing opportunities for further extensions.

Choosing adequate goals plays is central to the success of a task. With this study, we investigate tailoring the goals of a nutrition assistance system to the user's abilities according to a Rasch scale. To that end, we evaluated two versions of a mobile system that offers dietary tracking, visual feedback, and personalized recipe recommendations. The original version targets optimal nutritional behavior and focuses on the six least optimal nutrients (N=51). The adapted version targets only improved nutritional behavior compared to the status quo and thus tailors the advice to the next six achievable nutrients according to a Rasch scale (N=47). Results of the two-week study indicate that the tailored advice leads to higher success for the focused nutrients, and is perceived to be more diverse and personalized, and thus more effective.

HealthRecSys 2019 was the 4th International Workshop on Health Recommender Systems held in conjunction with the 2019 ACM Conference on Recommender Systems in Copenhagen, Denmark. This workshop followed on from of the previous workshop in 2018 [4] and focused on the application and potentials of recommender systems on health promotion, health care and health-related topics. By engaging the discussion and representation of health domains into recommender systems, this workshop facilitated the cross-domain collaborations and exchange of knowledge and infrastructure.

The 3rd International Workshop on Health Recommender Systems was held in conjunction with the 2018 ACM Conference on Recommender Systems in Vancouver, Canada. Following the two prior workshops in 2016 [4] and 2017 [2], the focus of this workshop is to deepen the discussion on health promotion, health care as well as health related methods. This workshop also aims to strengthen the HealthRecSys community, to engage representatives of other health domains into cross-domain collaborations, and to exchange and share infrastructure.

The 2017 Workshop on Health Recommender Systems was held in conjunction with the 2017 ACM Conference on Recommender Systems in Como, Italy. Following the fists workshop in 2016, the focus of this workshop was on enhancing the results of the first workshop by elaborating discussions on the topics, attracting scientist from other domains, finding cross-domain collaboration, and establishing shared infrastructures.

The first Workshop on Engendering Health with Recommender Systems was organized in conjunction with ACM RecSys 2016. The focus of the workshop was on bringing together researchers and practitioners from diverse areas of health, well-being, decision support, and behavioral change. Health-related issues in recommender systems have been a growing research topic in the recent years and this was a initial attempt at bringing together academics and practitioners to share their experiences on working on related issues.

Despite their high priority, healthy nutrition, physical activity and other preventive health factors are rarely adopted over a long term. Traditional nutrition support systems lack of practical everyday knowledge, social support and motivation as well the consideration of the personal context. We address these impediments with a holistic decision support system that empowers people to change their lifestyle successfully. We aim at analyzing previous approaches from various disciplines and integrating them into one concept for nutrition support giving personalized context aware recommendations to each user while presenting and teaching practical information about healthy nutrition. Additionally, we consider the ease of usage of such an application by automating necessary burdens and motivating participants with social incentives. The decision support system is tested in a 6-month intervention study using regression analysis on usage patterns and matrix factorial designs for interacting features. The social and interactive components are observed in a 1-year field study, utilizing a realistic environment.

This papers proposes two novel approaches for the identification of Takagi-Sugeno fuzzy models with time variant and invariant features. The proposed Mixed Fuzzy Clustering algorithm is proposed for determining the parameters of Takagi-Sugeno fuzzy models in two different ways: (1) the antecedent fuzzy sets are determined based on the partition matrix generated by the Mixed Fuzzy Clustering algorithm; (2) the input features are transformed using the same algorithm and the antecedent fuzzy sets are derived using Fuzzy C-Means clustering. The proposed approaches are tested on four different health care applications: readmissions in intensive care units, administration of vasopressors and mortality. The results show that the proposed clustering algorithm resulted in an increase of the performance of the fuzzy models in three out of four applications in comparison to the use of Fuzzy C-Means.

The current demands on the energy market, such as efficiency, sustainability and affordability increase the need for customer understanding and data analysis. This paper presents an analysis of the segmentation of electricity consumers based on the fuzzy clustering of time variant electricity consumption data and invariant features like the demographic customer information. The algorithm used is mixed fuzzy clustering (MFC), which allows integrating both variant and invariant features into one clustering. The clustering is evaluated both in its stability over the two years of data, using a entropy measurement and in its general quality given by the three clustering validity indices, Calinski-Harabasz, Davies-Bouldin and Silhouette index.

Visualization and interactive analysis can help network administrators and security analysts analyze the network flow and log data. The complexity of such an analysis requires a combination of knowledge and experience from more domain experts to solve difficult problems faster and with higher reliability. We developed an online visual analysis system called OCEANS to address this topic by allowing close collaboration among security analysts to create deeper insights in detecting network events. Loading the heterogeneous data source (netflow, IPS log and host status log), OCEANS provides a multi-level visualization showing temporal overview, IP connections and detailed connections. Participants can submit their findings through the visual interface and refer to others' existing findings. Users can gain inspiration from each other and collaborate on finding subtle events and targeting multi-phase attacks. Our case study confirms that OCEANS is intuitive to use and can improve efficiency. The crowd collaboration helps the users comprehend the situation and reduce false alarms.