Filtered by themeUser modeling14 papersclear ✕

Does personality matter: examining the value of personality insights for personalized nudges that encourage the selection of learning resourcesCardenas Canto, dimitrova · 2024© 2024 Cardenas Canto, Dimitrova, Sherman and Flint. This is an open-access article distributed under the terms of the Creative Commons Attribution License CC BY. The use, distribution or reproduction in other forums is permitted, provided the original author(s) and the copyright owner(s) are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms.

UX of AI & PersonalizationResearch Papers

MineXR: Mining Personalized Extended Reality InterfacesHyunsung Cho · 2024Extended Reality (XR) interfaces offer engaging user experiences, but their effective design requires a nuanced understanding of user behavior and preferences. This knowledge is challenging to obtain without the widespread adoption of XR devices. We intro­ duce MineXR, a design mining workflow and data analysis platform for collecting and analyzing personalized XR user interaction and This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike International 4.0 License. CHI ’24, May 11–16, 2024, Honolulu, HI, USA © 2024 Copyright held by the owner/author(s). ACM ISBN 979-8-4007-0330-0/24/05 https://doi.org/10.1145/3613904.3642394 experience data. MineXR enables elicitation of personalized in­ terfaces from participants of a data collection: for any particular context, participants create interface elements using application screenshots from their own smartphone, place them in the envi­ ronment, and simultaneously preview the resulting XR layout on a headset. Using MineXR, we contribute a dataset of personalized XR interfaces collected from 31 participants, consisting of 695 XR widgets created from 178 unique applications. We provide insights for XR widget functionalities, categories, clusters, UI element types, and placement. Our open-source tools and data support researchers and designers in developing future XR interfaces. CCS CONCEPTS • Human-centered computing → Mixed / augmented reality; Systems and tools for interaction design. CHI ’24, May 11–16, 2024, Honolulu, HI, USA Cho et al.

UX of AI & PersonalizationResearch Papers

How Well Does the Algorithm Know Me?Julia Graefe · 2022The use of artificial intelligence (AI) in everyday products increases and thereby also the interest on human-AI interaction. Research on user-adaptive systems still lacks uniform terminology and common definitions. To fill this gap, a taxonomy of user-adaptive systems, the Levels of Adaptive Sensitive Responses (LASR), has been proposed in previous research. The LASR levels are a first step towards a uniform classification of user-adaptive systems, but still need to be validated in terms of comprehensiveness and accuracy. This paper presents an evaluation of the LASR taxonomy through its application on technical products, to examine whether the taxonomy is complete and applicable in a meaningful way. We used a four steps analysis approach, covering the definition of classification criteria, two research iterations on suitable user-adaptive product features, and the analysis to which degree these features fulfill the classification criteria. As a result, our analysis shows that nine out of eleven analyzed product features can clearly be categorized into one of the five levels of LASR. Two features showed characteristics of two different levels which reveals that the levels are not mutually exclusive but can be combined within one product feature.

UX of AI & PersonalizationResearch Papers

Editorial: Psychological Models for Personalized Human-Computer Interaction (HCI)Anton Nijholt · 2021The behavior of users in the digital world, such as online shopping or social media activity, is increasingly supported by personalized systems, such as recommender systems \(Ricci et al., 2015\) and personalized learning. Early work on personalized systems was mainly data-driven, based on behavioral data, such as ratings, likes, and purchases (e.g., Bell et al., 2007\). Although these systems are useful for both users and service providers, the main downside is the limited interpretability and explainability of the data. Such limitations in both interpretability and explainability translate in using data without understanding the root-cause of behaviors. Recent work has thus started to adopt a more theory-driven approach by including psychological theories and models to improve personalized systems (see for an overview; Graus and Ferwerda, 2019\). These systems take advantage of psychological theories/models, such as emotions (Tkalci ˇ c et al., 2013b; Tkal ˇ ci ˇ c and ˇ Ferwerda, 2018\), personality \(Ferwerda et al., 2017; Wu et al., 2018\), skills \(Ferwerda and Graus, 2018\), and culture \(Schedl et al., 2017\) to explain and predict behaviors of users. This allows for a deeper understanding of users' behavior, preferences, and needs, which in turn also lead to more generalizable results.

UX of AI & PersonalizationResearch Papers

Physiology-based personalization of persuasive technology: a user modeling perspectiveSpelt · 2021Persuasive technology (PT) can assist in behavior change. PT systems often rely on user models, based on behavior and self-report data, to personalize their function- alities and thereby increase efficiency. This review paper shows how physiological measurements could be used to further improve user models for personalization of PT by means of bio-cybernetic loops and data-driven approaches. Furthermore, we outline the advantages of using physiological measures for personalization compared to self-report and behavior measurement. Additionally, we show how two types of physiological information—physiological states and physiological reactivity—can be relevant for PT adaptations. To illustrate this, we present a model with two types of physiology-based PT adaptations as part of a bio-cybernetic loop; state-based and reactivity-based. Next, we discuss the implications of physiology-aware PT for per- suasive design and theory. And lastly, because of the potential impact of such systems, we also consider important ethical implications of physiology-aware PT. B Hanne A. A. Spelt [hanne.spelt@philips.com](mailto:hanne.spelt@philips.com); [h.a.a.spelt@tue.nl](mailto:h.a.a.spelt@tue.nl) Joyce H. D. M. Westerink [joyce.westerink@philips.com](mailto:joyce.westerink@philips.com); [j.h.d.m.westerink@tue.nl](mailto:j.h.d.m.westerink@tue.nl) Lily Frank [l.e.frank@tue.nl](mailto:l.e.frank@tue.nl) Jaap Ham [j.r.c.ham@tue.nl](mailto:j.r.c.ham@tue.nl) Wijnand A. IJsselsteijn [w.a.ijsselsteijn@tue.nl](mailto:w.a.ijsselsteijn@tue.nl) 1 Digital Engagement, Cognition & Behavior Group, Philips Research, High Tech Campus 34, 5656 AE Eindhoven, The Netherlands 2 Human-Technology Interaction Group, Faculty Industrial Engineering & Innovation Sciences, Eindhoven University of Technology, Postbus 513, 5600 MB Eindhoven, The Netherlands 3 Philosophy & Ethics Group, Faculty Industrial Engineering & Innovation Sciences, Eindhoven University of Technology, Postbus 513, 5600 MB Eindhoven, The Netherlands 123 134 H. A. A. Spelt et al.

UX of AI & PersonalizationResearch Papers

User Context Ontology for Adaptive Mobile-Phone InterfacesReceived June · 2021The Adaptive User Interface (AUI) adapts to the changes in the context of use and provides improved interaction abilities for different users. The adaptivity in the user interfaces requires in depth knowledge of context. There is a need to enrich user profiles to achieve the personalized services with the ability to adapt the user’s context. The context can be reflected in a particular kind of knowledge and hence modeled as ontology. Ontology based context models are effective means to handle complex situations that support the sharing or integration of context information. This paper presents ontology based context model using OWL for adaptive mobile devices. It models the context over its four major elements including device, user, environment (location and time) and activity. The proposed ontology was derived in different classes, relationships, associations, dependencies and constraints to model dynamic context. Ontologies present a standardized, consistent and shareable context model. The context model and consequent context snapshots can be acknowledged by AUI to present a suitable user interface. The ontology was developed using Protégé on the basis of each context type having different values. Semantic querying (SPARQL) was used for knowledge acquisition. Moreover, the Pellet and HermiT Reasoner were used to verify the rules, relations and constraints to avoid the inconsistency between classes. Comparative to other context models for adaptive interfaces, ontological model provides more of scalability and growth with learning new context in to the shared context knowledge. INDEX TERMS Adaptive user interface, context aware interface, ontology driven interfaces, knowledge representation, knowledge engineering.

UX of AI & PersonalizationResearch Papers

Towards User-Centric Intervention Adaptiveness: Influencing Behavior-Context Based Healthy Lifestyle InterventionsReceived September · 2020In the era of digital well-being, smart gadgets are the unobtrusive sources of acquiring infor- mation. A variety of personalized wellness applications support self-quantification based recommendations to provide wellness status for achieving personalized targets. However, these applications are unable to promote the induction of new healthy habits and thus are not too much effective for long term as users tend to loose their interest. Thus, we have proposed a methodology for User-Centric Adaptive Intervention based on behavior change theory for maintaining end-users’ interest. The methodology consists of four steps: (1) quantification of behavior based on contributing factors governed by expert-driven rules; (2) behavior-context based mapping for the identification of behavior status of the user; (3) selection of appropriate way of intervention to get fruitful outcomes; and finally (4) feedback based evaluation on the basis of recorded activities and questionnaires for satisfaction. A comprehensive healthy behavior index- based quantification supports the machine learning-based prediction model for behavior-context mapping. Furthermore, the evaluation is performed through implicit and explicit feedback analysis along with the accuracy of the behavior-context prediction model through multiple scenarios to cover comprehensive situations. The ensemble classifier suggests the accuracy of 98.02% for the behavior-context prediction model, which is higher than the other classifiers. The gain in behavior change is drawn from implicit feedback, which depicts that behavior context-based methods have improved the adaptation in behavior at a steady pace for the long term. The explicit feedback from 99 end-users of wellness application based on the proposed methodology obtained Good and Desired status for widely used System Usability Score and AttrakDiff tools respectively. INDEX TERMS User behavior, behavior-context, lifestyle, lifelog monitoring, self-quantification, healthy behavior index, adaptive interventions.

UX of AI & PersonalizationResearch Papers

Individualising Graphical Layouts with Predictive Visual Search ModelsKRIS LUYTEN · 2019In domains where users are exposed to large variations in visuo-spatial features among designs, they often spend excess time searching for common elements (features) on an interface. This article contributes individualised predictive models of visual search, and a computational approach to restructure graphical layouts for an individual user such that features on a new, unvisited interface can be found quicker. It explores four technical principles inspired by the human visual system (HVS) to predict expected positions of features and create individualised layout templates: (I) the interface with highest frequency is chosen as the template; (II) the interface with highest predicted recall probability (serial position curve) is chosen as the template; (III) the most probable locations for features across interfaces are chosen (visual statistical learning) to generate the template; (IV) based on a generative cognitive model, the most likely visual search locations for features are chosen (visual sampling modelling) to generate the template. Given a history of previously seen interfaces, we restructure the spatial layout of a new (unseen) interface with the goal of making its features more easily findable. The four HVS principles are implemented in Familiariser, a web browser that automatically restructures webpage layouts based on the visual history of the user. Evaluation of Familiariser (using visual statistical learning) with users provides first evidence that our approach reduces visual search time by over 10%, and number of eye-gaze fixations by over 20%, during web browsing tasks.

UX of AI & PersonalizationResearch Papers

Familiarisation: Restructuring Layouts with Visual Learning ModelsKashyap Todi · 2018In domains where users are exposed to large variations in visuo-spatial features among designs, they often spend excess time searching for common elements (features) in familiar locations. This paper contributes computational approaches to restructuring layouts such that features on a new, unvisited interface can be found quicker. We explore four concepts of fa- miliarisation, inspired by the human visual system (HVS), to automatically generate a familiar design for each user. Given a history of previously visited interfaces, we restructure the spatial layout of the new (unseen) interface with the goal of making its elements more easily found. Familiariser is a browser-based implementation that automatically restruc- tures webpage layouts based on the visual history of the user. Our evaluation with users provides first evidence favouring familiarisation. Author Keywords Visual search; Graphical layouts; Computational design; Adaptive user interfaces

UX of AI & PersonalizationResearch Papers

Towards incorporating personality into the design of an interface: a method for facilitating users' interaction with the displaySamer Muthana Sarsam, Hosam Al-Samarraie · 2018A novel user interface (UI) design based on the personality characteristics of users was proposed and examined in a mobile learning context. It was argued that differences in personality can stimulate individuals’ information processing capabili- ties in according to their display preferences, thus an effective visual experience. The personality characteristics and design preferences of 87 students (37 male, and 50 female) were collected and analysed. The clustering result (using k-means algorithm) revealed two potential personality types, which we call the neuroticism and the extra- conscientiousness groups. Then, an interface was designed for each personality group using the association rules method. An eye-tracking device was used to record changes in participants’ eye-pupil diameter and fixation duration, and thus examine their cogni- tive load and attention. The participants’ eye movement data of each group showed that their visual experience was significantly improved when using the interface designed based on their personality characteristics. This work offers some important design and practical insights to the human–computer interaction and the design of mobile device UI.

UX of AI & PersonalizationResearch Papers

Adaptive user modelling in car racing games using behavioural and physiological dataTheodosis Georgiou, Yiannis Demiris · 2015Personalised content adaptation has great potential to increase user engage- ment in video games. Procedural generation of user-tailored content increases the self-motivation of players as they immerse themselves in the virtual world. An adap- tive user model is needed to capture the skills of the player and enable automatic game content altering algorithms to fit the individual user. We propose an adaptive user modelling approach using a combination of unobtrusive physiological data to iden- tify strengths and weaknesses in user performance in car racing games. Our system creates user-tailored tracks to improve driving habits and user experience, and to keep engagement at high levels. The user modelling approach adopts concepts from the Trace Theory framework; it uses machine learning to extract features from the user’s physiological data and game-related actions, and cluster them into low level primi- tives. These primitives are transformed and evaluated into higher level abstractions such as experience, exploration and attention. These abstractions are subsequently used to provide track alteration decisions for the player. Collection of data and feed- back from 52 users allowed us to associate key model variables and outcomes to user responses, and to verify that the model provides statistically significant decisions per- sonalised to the individual player. Tailored game content variations between users in our experiments, as well as the correlations with user satisfaction demonstrate that our algorithm is able to automatically incorporate user feedback in subsequent procedural content generation. B Theodosis Georgiou theodosis.georgiou08@imperial.ac.uk Yiannis Demiris y.demiris@imperial.ac.uk 1 Personal Robotics Laboratory, Department of Electrical and Electronic Engineering, Imperial College London, Exhibition Road, South Kensington, London SW7 2BT, UK 123 268 T. Georgiou, Y. Demiris

UX of AI & PersonalizationResearch Papers

Towards a Human-centered E-Commerce Personalization FrameworkMarios Belk · 2015This paper presents a personalization framework, namely PersonaWeb that adapts the visual and interaction design of E-Commerce Web environments based on human cognitive differences. In particular, it describes a user model formalization that incorporates a set of human cognitive factors (i.e., cognitive styles and working memory capacity) and an adaptation engine that personalizes the visual and interaction design attributes of E-Commerce product views. The proposed framework has been applied in a real-life E-Commerce Web-site and two subsequent user studies were conducted in which 135 users interacted with the personalized and the original (non-personalized) version of the same Web environment. Results indicate the added value of personalizing content and functionality of E-Commerce product views in terms of users’ task completion performance.

UX of AI & PersonalizationResearch Papers

Persuasive strategies and emotional states: towards designing personalized and emotion-adaptive persuasive systems2023Persuasive strategies have been widely operationalized in systems or applications to motivate behaviour change across diverse domains. However, no empirical evidence exists on whether or not persuasive strategies lead to certain emotions to inform which strategies are most appropriate for delivering interventions that not only motivate users to perform target behaviour but also help to regulate their current emotional states. We conducted a large-scale study of 660 participants to investigate if and how individ- uals including those at different stages of change respond emotionally to persuasive strategiesandwhy.Specifically,weexaminedtherelationshipbetweenperceivedeffec- tiveness of individual strategies operationalized in a system and perceived emotional states for participants at different stages of behaviour change. Our findings estab- lished relations between perceived effectiveness of strategies and emotions elicited in individuals at distinct stages of change and that the perceived emotions vary across stages of change for different reasons. For example, the reward strategy is associated with positive emotion only (i.e. happiness) for individuals across distinct stages of change because it induces feelings of personal accomplishment, provides incentives that increase the urge to achieve more goals, and offers gamified experience. Other strategies are associated with mixed emotions. Our work links emotion theory with behaviour change theories and stages of change theory to develop practical guidelines for designing personalized and emotion-adaptive persuasive systems. B Oladapo Oyebode oladapo.oyebode@dal.ca Darren Steeves darren@jackhabbit.com Rita Orji rita.orji@dal.ca 1 Faculty of Computer Science, Dalhousie University, Halifax, NS B3H 1W5, Canada 2 School of Health and Human Performance, Dalhousie University, Halifax, NS B3H 4R2, Canada 123 1176 O. Oyebode et al.

Emotional DesignResearch Papers

Computer Science ReviewMaaruf Ali, Peter S. Excell · 2021A review of research on universal usability, plasticity of user interface design and facilitation of interface development with universal usability is presented. The survey was based on 165 research papers spanning over fifty-five years. The foundations of adaptive or intelligent user interfaces (AUI or IUI) are presented, three core domains being focused upon: Artificial Intelligence (AI), User Modelling (UM) and Human–Computer Interaction (HCI). For comparison of the various AUIs, a proposed taxonomy is given. One conclusion is that an efficient training vector for fast optimal convergence of the machine-learning algorithm is a necessity, but key to this is the bounding of the dataset, the goal being to achieve an accurate user preference model, which has to be built from a limited number of datasets obtained from the human interaction. More research also needs to be conducted to ascertain the usefulness and effectiveness of IUIs compared against AUIs. With the global mobility of users, interface design must take account of the abilities and cultures of users, derived from actual user behaviour and not on their feedback. A key question is whether the interface should be adaptive under system control or be made adaptable under user control. A need is identified for an ‘‘afferential component’’ that stores a priori information about the end user, an ‘‘inferential component’’ that determines to what extent the user interface actually needs to be adapted, and the ‘‘efferential component’’ that actually determines how the adaptivity is applied seamlessly to the system. Application to e-learning is a priority: the use of machine intelligence to achieve appropriate learnability, ideally enhanced by ‘‘Playful interaction’’, was found to be desirable. Universal application of adaptation lies in the future, but AUI properties cannot be ascertained while disregarding the other parameters of the system in which it will be used. A more complete understanding of the human mental model is necessary, requiring a highly multidisciplinary approach and cooperation between diverse researchers. Finally, a performance evaluation of plasticity of user interface was conducted: it is concluded that the use of dynamic techniques can enhance the user experience to a much greater extent than more basic approaches, although optimisation of usability parameter trade-offs needs further attention. It is noted that most of the work reviewed originated from a limited range of cultural pe

HCI & Adaptive InterfacesResearch Papers