Large language models (LLMs) are increasingly used as automated evaluators (LLM-as-a-Judge). This work challenges its reliability by showing that trust judgments by LLMs are biased by disclosed source labels. Using a counterfactual design, we find that both humans and LLM judges assign higher trust to information labeled as human-authored than to the same content labeled as AI-generated. Eye-tracking data reveal that humans rely heavily on source labels as heuristic cues for judgments. We analyze LLM internal states during judgment. Across label conditions, models allocate denser attention to the label region than the content region, and this label dominance is stronger under Human labels than AI labels, consistent with the human gaze patterns. Besides, decision uncertainty measured by logits is higher under AI labels than Human labels. These results indicate that the source label is a salient heuristic cue for both humans and LLMs. It raises validity concerns for label-sensitive LLM-as-a-Judge evaluation, and we cautiously raise that aligning models with human preferences may propagate human heuristic reliance into models, motivating debiased evaluation and alignment.

Artificial intelligence is increasingly diffusing into design and creative education, reshaping how students ideate, iterate, and produce work. While these tools offer clear benefits in terms of speed and experimentation, they also challenge long-standing pedagogical assumptions regarding the importance of process, authorship, and studio-based learning. Educators are therefore faced with a dual task: mitigating the risks AI poses to reflective, process-oriented design while simultaneously exploring ways to meaningfully integrate these technologies into curricula. Through working group activities, this workshop examines these tensions to identify emerging strategies for the critical and transparent use of AI. Ultimately, we aim to address current knowledge gaps, establish a collaborative research agenda, and build a network to support AI collaboration in design and creative education.

Within journalistic editorial processes, disclosing AI usage is currently limited to simplistic labels, which misses the nuance of how humans and AI collaborated on a news article. Through co-design sessions (N=10), we elicited 69 disclosure designs and implemented four prototypes that visually disclose human–AI collaboration in journalism. We then ran a within-subjects lab study (N=32) to examine how disclosure visualizations (Textual, Role-based Timeline, Task-based Timeline, Chatbot) and collaboration ratios (Primarily Human vs. Primarily AI) influenced visualization perceptions, gaze patterns, and post-experience responses. We found that textual disclosures were least effective in communicating human-AI collaboration, whereas Chatbot offered the most in-depth information. Furthermore, while role-based timelines amplified AI contribution in primarily human articles, task-based timeline shifted perceptions toward human involvement in primarily AI articles. We contribute Human-AI collaboration disclosure visualizations and their evaluation, and cautionary considerations on how visualizations can alter perceptions of AI’s actual role during news article creation.

Modeling users' cognitive states (e.g., cognitive load and decision confidence) is essential for building adaptive AI in high-stakes decision-making. While eye tracking provides non-invasive behavioral signals correlated with cognitive effort, prior work has not systematically examined how AI assistance contexts, specifically varying advice reliability and user heterogeneity, can alter the mapping between gaze signals and cognitive states. We conducted a within-subject lab eye-tracking study (N=54) on factual verification tasks under three conditions: No-AI, Correct-AI advice, and Incorrect-AI advice. We analyze condition-dependent changes in self-reports and eye-tracking patterns and evaluate the robustness of eye-tracking-based user modeling. Results show that AI advice increases decision confidence compared to No-AI, while Correct-AI is associated with lower perceived cognitive load and more efficient gaze behavior. Crucially, predictive modeling is context-sensitive: the relationship between eye-tracking signals and cognitive states shifts across AI conditions. Finally, fusing eye-tracking features with user priors (demographics, AI literacy/experience, and propensity to trust technology) improves cross-participant generalization. These findings support condition-aware and personalized user modeling for cognitively aligned adaptive AI systems.

As AI-generated health information proliferates online and becomes increasingly indistinguishable from human-sourced information, it becomes critical to understand how people trust and label such content, especially when the information is inaccurate. We conducted two complementary studies: (1) a mixed-methods survey (N=142) employing a 2 (source: Human vs. LLM) × 2 (label: Human vs. AI) × 3 (type: General, Symptom, Treatment) design, and (2) a within-subjects lab study (N=40) incorporating eye-tracking and physiological sensing (ECG, EDA, skin temperature). Participants were presented with health information varying by source-label combinations and asked to rate their trust, while their gaze behavior and physiological signals were recorded. We found that LLM-generated information was trusted more than human-generated content, whereas information labeled as human was trusted more than that labeled as AI. Trust remained consistent across information types. Eye-tracking and physiological responses varied significantly by source and label. Machine learning models trained on these behavioral and physiological features predicted binary self-reported trust levels with 73 % accuracy and information source with 65 % accuracy. Our findings demonstrate that adding transparency labels to online health information modulates trust. Behavioral and physiological features show potential to verify trust perceptions and indicate if additional transparency is needed.

Encounters with virtual agents currently lack the haptic viscerality of human contact. While digital biosignal communication can medi-ate such virtual social interactions, how artifcial haptic biosignals infuence users personal space during Virtual Reality (VR) experi-ences is unknown. Designing vibrotactile heartbeats and thermally-actuated body temperature, we ran a within-subjects study (N=31) to investigate feedback (Thermal, Vibration, Thermal+Vibration, None) and agent stories (Negative, Neutral, Positive) on objective and subjective interpersonal distance (IPD), perceived arousal and comfort, presence, and post-experience responses. Findings showed that thermal feedback decreased objective but not subjective IPD, whereas vibrotactile heartbeats (signaling agent's closeness) increased both while heightening arousal and discomfort. Agents stories did not afect IPD, arousal, or comfort. Our qualitative fndings shed light on signal ambiguity and presence constructs within VR-based haptic stimulation. We contribute insights into artifcial biosignals and their infuence on VR proxemics, with cautionary considerations should the boundaries blur between physical and virtual touch.

Recent advancements in large language models (LLMs) have shown promise in generating psychotherapeutic dialogues, particularly in the context of motivational interviewing (MI). However, the inherent lack of transparency in LLM outputs presents significant challenges given the sensitive nature of psychotherapy. Applying MI strategies, a set of MI skills, to generate more controllable therapeutic-adherent conversations with explainability provides a possible solution. In this work, we explore the alignment of LLMs with MI strategies by first prompting the LLMs to predict the appropriate strategies as reasoning and then utilizing these strategies to guide the subsequent dialogue generation. We seek to investigate whether such alignment leads to more controllable and explainable generations. Multiple experiments including automatic and human evaluations are conducted to validate the effectiveness of MI strategies in aligning psychotherapy dialogue generation. Our findings demonstrate the potential of LLMs in producing strategically aligned dialogues and suggest directions for practical applications in psychotherapeutic settings.

As immersive 360° video experiences through head-mounted displays (HMDs) gain widespread adoption, the need for real-time, fine-grained assessment of Quality of Experience (QoE) becomes increasingly critical for optimising user engagement and system performance. This paper introduces RCQoEA-360VR, a novel multi-modal dataset designed for continuous QoE evaluation in virtual reality (VR) environments. In a controlled study (N=32), participants watched five selected 360° video sequences across eight different video quality configurations (from the VQEG database) using a Vive Pro Eye while providing continuous QoE annotations via a touchpad-based input method, enhanced by the DotMorph peripheral visualisation technique. The dataset also includes synchronised physiological signals (electrocardiogram and galvanic skin response), behavioural data (eye and head movements) and post-viewing QoE ratings gathered through a within-VR interface. RCQoEA-360VR addresses a critical gap in existing public datasets by providing a fine-grained, synchronised multimodal data for immersive QoE analysis. It offers a unique and valuable resource for the research community, supporting a wide range of research applications, including QoE prediction, behavioural modelling, adaptive streaming, and implicit perceptual analysis.

Artificial Intelligence (AI) is revolutionizing the way content is produced and integrated into journalistic workflows. The EU AI act’s Article 50 sets up transparency requirements aimed at encouraging the adoption and disclosure of AI in an ethical and responsible manner. In this study, we organized focus group interviews with Dutch citizens (N=21) to understand their expectations and needs regarding AI disclosures in the context of news production and journalism. These conversations are essential to understand if legal and regulatory policies are grounded in real-world experiences of citizens, and adequately address their concerns and enhance their digital interactions. We found that citizens predominantly favor disclosures of AI usage in journalistic content, in the form of (1) source references, (2) visual indicators (logos/watermarks) and (3) have varying preferences regarding information presentation and interaction modalities. Our findings highlight the need for interdisciplinary approaches to align standardization efforts with AI disclosures for news media.

Chatbots or conversational agents (CAs) are increasingly used to improve access to digital psychotherapy. Many current systems rely on rigid, rule-based designs, heavily dependent on expert-crafted dialogue scripts for guiding therapeutic conversations. Although advances in large language models (LLMs) offer potential for more flexible interactions, their lack of controllability and explanability poses challenges in high-stakes contexts like psychotherapy. To address this, we conducted two studies in this work to explore how aligning LLMs with expert-crafted scripts can enhance psychotherapeutic chatbot performance. In Study 1 (N=43), an online experiment with a within-subjects design, we compared rule-based, pure LLM, and LLMs aligned with expert-crafted scripts via fine-tuning and prompting. Results showed that aligned LLMs significantly outperformed the other types of chatbots in empathy, dialogue relevance, and adherence to therapeutic principles. Building on findings, we proposed ''Script-Strategy Aligned Generation (SSAG)'', a more flexible alignment approach that reduces reliance on fully scripted content while maintaining LLMs' therapeutic adherence and controllability. In a 10-day field Study 2 (N=21), SSAG achieved comparable therapeutic effectiveness to full-scripted LLMs while requiring less than 40% of expert-crafted dialogue content. Beyond these results, this work advances LLM applications in psychotherapy by providing a controllable and scalable solution, reducing reliance on expert effort. By enabling domain experts to align LLMs through high-level strategies rather than full scripts, SSAG supports more efficient co-development and expands access to a broader context of psychotherapy.

Among creative professionals, Generative Artificial Intelligence (GenAI) has sparked excitement over its capabilities and fear over unanticipated consequences. How does GenAI impact User Experience Design (UXD) practice, and are fears warranted? We interviewed 20 UX Designers, with diverse experience and across companies (startups to large enterprises). We probed them to characterize their practices, and sample their attitudes, concerns, and expectations. We found that experienced designers are confident in their originality, creativity, and empathic skills, and find GenAI’s role as assistive. They emphasized the unique human factors of “enjoyment” and “agency”, where humans remain the arbiters of “AI alignment’’. However, skill degradation, job replacement, and creativity exhaustion can adversely impact junior designers. We discuss implications for human-GenAI collaboration, specifically copyright and ownership, human creativity and agency, and AI literacy and access. Through the lens of responsible and participatory AI, we contribute a deeper understanding of GenAI fears and opportunities for UXD.

Virtual co-embodiment enables two users to share a single avatar in Virtual Reality (VR). During such experiences, the illusion of shared motion control can break during joint-action activities, highlighting the need for position-aware feedback mechanisms. Drawing on the perceptual crossing paradigm, we explore how haptics can enable non-verbal coordination between co-embodied participants. In a within-subjects study (20 participant pairs), we examined the effects of vibrotactile haptic feedback (None, Present) and avatar control distribution (25-75%, 50-50%, 75-25%) across two VR reaching tasks (Targeted, Free-choice) on participants’ Sense of Agency (SoA), co-presence, body ownership, and motion synchrony. We found (a) lower SoA in the free-choice with haptics than without, (b) higher SoA during the shared targeted task, (c) co-presence and body ownership were significantly higher in the free-choice task, (d) players’ hand motions synchronized more in the targeted task. We provide cautionary considerations when including haptic feedback mechanisms for avatar co-embodiment experiences.

MobiTouch is a wearable haptic device that integrates pneumatic and vibrotactile technologies to enhance touch sensations. The system addresses the slow responsiveness of small pneumatic components by compensating with vibrations, allowing for more diverse touch patterns. The wrist prototype operates wireless, is powered by a rechargeable battery, and features customisable touch patterns through an external controller. MobiTouch’s design improves portability and responsiveness for haptic pneumatic wearables, offering potential applications in affective touch and wireless tactile transmission.

Biosensing technologies are on their way to becoming ubiquitous in multimedia interaction.These technologies capture physiological data, such as heart rate, breathing, skin conductance, and brain activity.Researchers are exploring biosensing from perspectives including engineering, design, medicine, mental health, consumer products, and interactive art.These technologies can enhance our interactions, allowing us to connect with our bodies and others around us across diverse application areas.However, the integration of biosignals in HCI presents new challenges pertaining to choosing what data we capture, interpreting these data, its representation, application areas, and ethics.There is a need to synthesize knowledge across diverse perspectives of researchers and designers spanning multiple domains and to map a landscape of the challenges and opportunities of this research area.The goal of this workshop is to exchange knowledge in the research community, introduce novices to this emerging field, and build a future research agenda.

Eliciting and capturing drivers’ affective responses in a realistic outdoor setting with pedestrians poses a challenge when designing in-vehicle, empathic interfaces. To address this, we designed a controlled, outdoor car driving circuit where drivers (N=27) drove and encountered pedestrian confederates who performed non-verbal positive or non-positive road crossing actions towards them. Our findings reveal that drivers reported higher valence upon observing positive, non-verbal crossing actions, and higher arousal upon observing non-positive crossing actions. Drivers’ heart signals (BVP, IBI and BPM), skin conductance and facial expressions (brow lowering, eyelid tightening, nose wrinkling, and lip stretching) all varied significantly when observing positive and non-positive actions. Our car driving study, by drawing on realistic driving conditions, further contributes to the development of in-vehicle empathic interfaces that leverage behavioural and physiological sensing. Through automatic inference of driver affect resulting from pedestrian actions, our work can enable novel empathic interfaces for supporting driver emotion self-regulation.

Capturing drivers’ affective responses given driving context and driver-pedestrian interactions remains a challenge for designing in-vehicle, empathic interfaces. To address this, we conducted two lab-based studies using camera and physiological sensors. Our first study collected participants’ (N = 21) emotion self-reports and physiological signals (including facial temperatures) toward non-verbal, pedestrian crossing videos from the Joint Attention for Autonomous Driving dataset. Our second study increased realism by employing a hybrid driving simulator setup to capture participants’ affective responses (N = 24) toward enacted, non-verbal pedestrian crossing actions. Key findings showed: (a) non-positive actions in videos elicited higher arousal ratings, whereas different in-video pedestrian crossing actions significantly influenced participants’ physiological signals. (b) Non-verbal pedestrian interactions in the hybrid simulator setup significantly influenced participants’ facial expressions, but not their physiological signals. We contribute to the development of in-vehicle empathic interfaces that draw on behavioral and physiological sensing to in-situ infer driver affective responses during non-verbal pedestrian interactions.

During group interactions, we react and modulate our emotions and behaviour to the group through phenomena including emotion contagion and physiological synchrony. Previous work on emotion recognition through video/image has shown that group context information improves the classification performance. However, when using physiological data, literature mostly focuses on intrapersonal models that leave-out group information, while interpersonal models are unexplored. This paper introduces a new interpersonal Weighted Group Synchrony approach, which relies on Electrodermal Activity (EDA) and Heart-Rate Variability (HRV). We perform an analysis of synchrony metrics applied across diverse data representations (EDA and HRV morphology and features, recurrence plot, spectrogram), to identify which metrics and modalities better characterise physiological synchrony for emotion recognition. We explored two datasets (AMIGOS and K-EmoCon), covering different group sizes (4 vs dyad) and group-based activities (video-watching vs conversation). The experimental results show that integrating group information improves arousal and valence classification, across all datasets, with the exception of K-EmoCon on valence. The proposed method was able to attain mean M-F1 of$\approx$72.15% arousal and 81.16% valence for AMIGOS, and M-F1 of$\approx$52.63% arousal, 65.09% valence for K-EmoCon, surpassing previous work results for K-EmoCon on arousal, and providing a new baseline on AMIGOS for long-videos.

Instead of predicting just one emotion for one activity (e.g., video watching), fine-grained emotion recognition enables more temporally precise recognition. Previous works on fine-grained emotion recognition require segment-by-segment, fine-grained emotion labels to train the recognition algorithm. However, experiments to collect these labels are costly and time-consuming compared with only collecting one emotion label after the user watched that stimulus (i.e., the post-stimuli emotion labels). To recognize emotions at a finer granularity level when trained with only post-stimuli labels, we propose an emotion recognition algorithm based on Deep Multiple Instance Learning (EDMIL) using physiological signals.EDMILrecognizes fine-grained valence and arousal (V-A) labels by identifying which instances represent the post-stimuli V-A annotated by users after watching the videos. Instead of fully-supervised training, the instances are weakly-supervised by the post-stimuli labels in the training stage. The V-A of instances are estimated by the instance gains, which indicate the probability of instances to predict the post-stimuli labels. We testedEDMILon three different datasets,CASE,MERCAandCEAP-360VR, collected in three different environments: desktop, mobile and HMD-based Virtual Reality, respectively. Recognition results validated with the fine-grained V-A self-reports show that for subject-independent 3-class classification (high/neutral/low),EDMILobtains promising recognition accuracies: 75.63% and 79.73% for V-A onCASE, 70.51% and 67.62% for V-A onMERCAand 65.04% and 67.05% for V-A onCEAP-360VR. Our ablation study shows that all components ofEDMILcontribute to both the classification and regression tasks. Our experiments also show that (1) compared with fully-supervised learning, weakly-supervised learning can reduce the problem of overfitting caused by the temporal mismatch between fine-grained annotations and physiological signals, (2) instance segment lengths between 1-2 s result in the highest recognition accuracies and (3)EDMILperforms best if post-stimuli annotations consist of less than 30% or more than 60% of the entire video watching.

Watching 360$^\circ$videos using Virtual Reality (VR) head-mounted displays (HMDs) provides interactive and immersive experiences, where videos can evoke different emotions. Existing emotion self-report techniques within VR however are either retrospective or interrupt the immersive experience. To address this, we introduce theContinuous Physiological and Behavioral Emotion Annotation Dataset for 360$^\circ$Videos (CEAP-360VR). We conducted a controlled study (N=32) where participants used a Vive Pro Eye HMD to watch eight validated affective 360$^\circ$video clips, and annotated their valence and arousal (V-A) continuously. We collected (a) behavioral (head and eye movements; pupillometry) signals (b) physiological (heart rate, skin temperature, electrodermal activity) responses (c) momentary emotion self-reports (d) within-VR discrete emotion ratings (e) motion sickness, presence, and workload. We show the consistency of continuous annotation trajectories and verify their mean V-A annotations. We find high consistency between viewed 360$^\circ$video regions across subjects, with higher consistency for eye than head movements. We furthermore run baseline classification experiments, where Random Forest classifiers with 2s segments show good accuracies for subject-independent models: 66.80% (V) and 64.26% (A) for binary classification; 49.92% (V) and 52.20% (A) for 3-class classification. Our open dataset allows further experiments with continuous emotion self-reports collected in 360$^\circ$VR environments, which can enable automatic assessment of immersive Quality of Experience (QoE) andmomentary affective states.

Fine-grained emotion recognition can model the temporal dynamics of emotions, which is more precise than predicting one emotion retrospectively for an activity (e.g., video clip watching). Previous works require large amounts of continuously annotated data to train an accurate recognition model, however experiments to collect such large amounts of continuously annotated physiological signals are costly and time-consuming. To overcome this challenge, we propose an Emotion recognition algorithm based on Deep Siamese Networks (EmoDSN) which can rapidly converge on a small amount of training data, typically less than 10 samples per class (i.e., <10 shot). EmoDSN recognizes fine-grained valence and arousal (V-A) labels by maximizing the distance metric between signal segments with different V-A labels. We tested EmoDSN on three different datasets collected in three different environments: desktop, mobile and HMD-based virtual reality, respectively. The results from our experiments show that EmoDSN achieves promising results for both one-dimension binary (high/low V-A, 1D-2 C) and two-dimensional 5-class (four quadrants of V- A space + neutral, 2D-5 C) classification. We get an averaged accuracy of 76.04, 76.62 and 57.62% for 1D-2 C valence, 1D-2 C arousal, and 2D-5 C, respectively, by using only 5 shots of training data. Our experiments show that EmoDSN can achieve better results if we select training samples from the changing points of emotion or the ending moments of video watching.

Measuring interoception ('perceiving internal bodily states') has diagnostic and wellbeing implications. Since heartbeats are distinct and frequent, various methods aim at measuring cardiac interoceptive accuracy (CIAcc). However, the role of exteroceptive modalities for representing heart rate (HR) across screen-based and Virtual Reality (VR) environments remains unclear. Using a PolarH10 HR monitor, we develop a modality-dependent cardiac recognition task that modifies displayed HR. In a mixed-factorial design (N=50), we investigate how task environment (Screen, VR), modality (Audio, Visual, Audio-Visual), and real-time HR modifications (±15%, ±30%, None) influence CIAcc, interoceptive awareness, mind-body measures, VR presence, and post-experience responses. Findings showed that participants confused their HR with underestimates up to 30%; environment did not affect CIAcc but influenced mind-related measures; modality did not influence CIAcc, however including audio increased interoceptive awareness; and VR presence inversely correlated with CIAcc. We contribute a lightweight and extensible cardiac interoception measurement method, and implications for biofeedback displays.

Visualizing biosignals can be important for social Virtual Reality (VR), where avatar non-verbal cues are missing. While several biosignal representations exist, designing effective visualizations and understanding user perceptions within social VR entertainment remains unclear. We adopt a mixed-methods approach to design biosignals for social VR entertainment. Using survey (N=54), context-mapping (N=6), and co-design (N=6) methods, we derive four visualizations. We then ran a within-subjects study (N=32) in a virtual jazz-bar to investigate how heart rate (HR) and breathing rate (BR) visualizations, and signal rate, influence perceived avatar arousal, user distraction, and preferences. Findings show that skeuomorphic visualizations for both biosignals allow differentiable arousal inference; skeuomorphic and particles were least distracting for HR, whereas all were similarly distracting for BR; biosignal perceptions often depend on avatar relations, entertainment type, and emotion inference of avatars versus spaces. We contribute HR and BR visualizations, and considerations for designing social VR entertainment biosignal visualizations.

Watching HMD-based 360° video has become in-creasing popular as a medium for immersive viewing of photo-realistic content. To evaluate subjective video quality, researchers typically prompt users to provide an overall Quality of Experience (QoE) score after viewing a stimulus. However, since users can adjust their viewport throughout a 360° video, a higher level of spatiotemporal granularity is needed for adaptive 360° video streaming. To address this, we design several real-time, continuous QoE annotation input and peripheral visualization techniques, with the goal of minimizing mental workload and distraction during score acquisition. Drawing on two parallel co-design sessions with seven experts, we find that touchpad and joystick are most suitable for continuous input, with DotMorph (circle with tick label that varies in filling) for peripheral state feedback. We contribute design findings for testing QoE score acquisition techniques during HMD-based 360° video watching, which enable more precise optimization of adaptive video streaming quality.

Precise emotion ground truth labels for 360° virtual reality (VR) video watching are essential for fine-grained predictions under varying viewing behavior. However, current annotation techniques either rely on post-stimulus discrete self-reports, or real-time, continuous emotion annotations (RCEA) but only for desktop/mobile settings. We present RCEA for 360° VR videos (RCEA-360VR), where we evaluate in a controlled study (N=32) the usability of two peripheral visualization techniques: HaloLight and DotSize. We furthermore develop a method that considers head movements when fusing labels. Using physiological, behavioral, and subjective measures, we show that (1) both techniques do not increase users’ workload, sickness, nor break presence (2) our continuous valence and arousal annotations are consistent with discrete within-VR and original stimuli ratings (3) users exhibit high similarity in viewing behavior, where fused ratings perfectly align with intended labels. Our work contributes usable and effective techniques for collecting fine-grained viewport-dependent emotion labels in 360° VR.

Voice is a rich modality for conveying emotions, however emotional prosody production can be situationally or medically impaired. Since thermal displays have been shown to evoke emotions, we explore how thermal stimulation can augment perception of neutrally-spoken voice messages with affect. We designed ThermalWear, a wearable on-chest thermal display, then tested in a controlled study (N=12) the effects of fabric, thermal intensity, and direction of change. Thereafter, we synthesized 12 neutrally-spoken voice messages, validated (N=7) them, then tested (N=12) if thermal stimuli can augment their perception with affect. We found warm and cool stimuli (a) can be perceived on the chest, and quickly without fabric (4.7-5s) (b) do not incur discomfort (c) generally increase arousal of voice messages and (d) increase / decrease message valence, respectively. We discuss how thermal displays can augment voice perception, which can enhance voice assistants and support individuals with emotional prosody impairments.

Collecting accurate and precise emotion ground truth labels for mobile video watching is essential for ensuring meaningful predictions. However, video-based emotion annotation techniques either rely on post-stimulus discrete self-reports, or allow real-time, continuous emotion annotations (RCEA) only for desktop settings. Following a user-centric approach, we designed an RCEA technique for mobile video watching, and validated its usability and reliability in a controlled, indoor (N=12) and later outdoor (N=20) study. Drawing on physiological measures, interaction logs, and subjective workload reports, we show that (1) RCEA is perceived to be usable for annotating emotions while mobile video watching, without increasing users' mental workload (2) the resulting time-variant annotations are comparable with intended emotion attributes of the video stimuli (classification error for valence: 8.3%; arousal: 25%). We contribute a validated annotation technique and associated annotation fusion method, that is suitable for collecting fine-grained emotion annotations while users watch mobile videos.

Millions of photos are shared online daily, but the richness of interaction compared with face-to-face (F2F) sharing is still missing. While this may change with social Virtual Reality (socialVR), we still lack tools to measure such immersive and interactive experiences. In this paper, we investigate photo sharing experiences in immersive environments, focusing on socialVR. Running context mapping (N=10), an expert creative session (N=6), and an online experience clustering questionnaire (N=20), we develop and statistically evaluate a questionnaire to measure photo sharing experiences. We then ran a controlled, within-subject study (N=26 pairs) to compare photo sharing under F2F, Skype, and Facebook Spaces. Using interviews, audio analysis, and our questionnaire, we found that socialVR can closely approximate F2F sharing. We contribute empirical findings on the immersiveness differences between digital communication media, and propose a socialVR questionnaire that can in the future generalize beyond photo sharing.

Navigation systems for cyclists are commonly screen-based devices mounted on the handlebar which show map information. Typically, adult cyclists have to explicitly look down for directions. This can be distracting and challenging for children, given their developmental differences in motor and perceptual-motor abilities compared with adults. To address this issue, we designed different unimodal cues and explored their suitability for child cyclists through two experiments. In the first experiment, we developed an indoor bicycle simulator and compared auditory, light, and vibrotactile navigation cues. In the second experiment, we investigated these navigation cues in-situ in an outdoor practice test track using a mid-size tricycle. To simulate road distractions, children were given an additional auditory task in both experiments. We found that auditory navigational cues were the most understandable and the least prone to navigation errors. However, light and vibrotactile cues might be useful for educating younger child cyclists.

To recognize emotions using less obtrusive wearable sensors, we present a novel emotion recognition method that uses only pupil diameter (PD) and skin conductance (SC). Psychological studies show that these two signals are related to the attention level of humans exposed to visual stimuli. Based on this, we propose a feature extraction algorithm that extract correlation-based features for participants watching the same video clip. To boost performance given limited data, we implement a learning system without a deep architecture to classify arousal and valence. Our method outperforms not only state-of-art approaches, but also widely-used traditional and deep learning methods.

In this paper, we describe a user study in which pairs of users watch a video trailer and interact with each other, using two social Virtual Reality (sVR) systems, as well as in a face-to-face condition. The sVR systems are: Facebook Spaces, based on puppet-like customized avatars, and a video-based sVR system using photo-realistic virtual user representations. We collect subjective and objective data to analyze users' Quality of Experience (QoE) and compare their interaction in VR to that observed during the real-life scenario. Our results show that the experience delivered by the video-based sVR system is comparable with real-life settings, while the puppet-based avatars limit the perceived quality of the interaction. Our protocol for QoE assessment is fully documented to allow replication in similar experiments.

This paper investigates bias in coverage between Western and Arab media on Twitter after the November 2015 Beirut and Paris terror attacks. Using two Twitter datasets covering each attack, we investigate how Western and Arab media differed in coverage bias, sympathy bias, and resulting information propagation. We crowdsourced sympathy and sentiment labels for 2,390 tweets across four languages (English, Arabic, French, German), built a regression model to characterize sympathy, and thereafter trained a deep convolutional neural network to predict sympathy. Key findings show: (a) both events were disproportionately covered (b) Western media exhibited less sympathy, where each media coverage was more sympathetic towards the country affected in their respective region (c) Sympathy predictions supported ground truth analysis that Western media was less sympathetic than Arab media (d) Sympathetic tweets do not spread any further. We discuss our results in light of global news flow, Twitter affordances, and public perception impact.

Head-mounted devices (HMDs) for Virtual and Augmented Reality (VR/AR) enable us to alter our visual perception of the world. However, current devices suffer from a limited field of view (FOV), which becomes problematic when users need to locate out of view objects (e.g., locating points-of-interest during sightseeing). To address this, we developed and evaluated in two studies HaloVR, WedgeVR, HaloAR and WedgeAR, which are inspired by usable 2D off-screen object visualization techniques (Halo, Wedge). While our techniques resulted in overall high usability, we found the choice of AR or VR impacts mean search time (VR: 2.25s, AR: 3.92s) and mean direction estimation error (VR: 21.85°, AR: 32.91°). Moreover, while adding more out-of-view objects significantly affects search time across VR and AR, direction estimation performance remains unaffected. We provide implications and discuss the challenges of designing for VR and AR HMDs.

Current head-mounted displays (HMDs) for Virtual Reality (VR) and Augmented Reality (AR) have a limited field-of-view (FOV). This limited FOV further decreases the already restricted human visual range and amplifies the problem of objects going out of view. Therefore, we explore the utility of augmenting HMDs with RadialLight, a peripheral light display implemented as 18 radially positioned LEDs around each eye to cue direction towards out-of-view objects. We first investigated direction estimation accuracy of multi-colored cues presented on one versus two eyes. We then evaluated direction estimation accuracy and search time performance for locating out-of-view objects in two representative 360° video VR scenarios. Key findings show that participants could not distinguish between LED cues presented to one or both eyes simultaneously, participants estimated LED cue direction within a maximum 11.8° average deviation, and out-of-view objects in less distracting scenarios were selected faster. Furthermore, we provide implications for building peripheral HMDs.

Innovations often trigger objections before becoming widely accepted. This paper assesses whether a familiarisation over time can be expected for data glasses, too. While user attitudes towards those devices have been reported to be prevalently negative [14], it is still unclear, to what extent this initial, negative user attitude might impede adoption. However, indepth understanding is crucial for reducing barriers early in order to gain access to potential benefits from the technology. With this paper we contribute to a better understanding of factors affecting data glasses adoption, as well as current trends and opinions. Our multiple-year case study (N=118) shows, against expectations, no significant change towards a more positive attitude between 2014 and 2016. We complement these findings with an expert survey (N=51) investigating prognoses, challenges and discussing the relevance of social acceptability. We elicit and contrast a controversial spectrum of expert opinions, and assess whether initial objections can be overwritten. Our analysis shows that while social acceptability is considered relevant for the time being, utility and usability are more valued for long-term adoption.

Activity trackers are frequently used in health and well-being, but their application in effective interventions is challenging. While research for reasons of use and non-use is ongoing, little is known about the way activity trackers are used in everyday life and over longer periods. We analyzed data of 104 individuals over 14,413 use days, and in total over 2.5 years. We describe general tracker use, periodic changes and overall changes over time, and identify characteristic patterns. While the use of trackers shows large individual heterogeneity, from our findings we could identify and classify general patterns for activity tracker use such as try-and-drop, slow-starter, experimenter, hop-on hop-off, intermittent and power user. Our findings contribute to the body of knowledge towards the successful design of effective health technologies, health interventions, and long-term health applications.

Various off-screen visualization techniques that point to off-screen objects have been developed for small screen devices. A similar problem arises with head-mounted Augmented Reality (AR) with respect to the human field-of-view, where objects may be out of view. Being able to detect so-called out-of-view objects is useful for certain scenarios (e.g., situation monitoring during ship docking). To augment existing AR with this capability, we adapted and tested well-known 2D off-screen object visualization techniques (Arrow, Halo, Wedge) for head-mounted AR. We found that Halo resulted in the lowest error for direction estimation while Wedge was subjectively perceived as best. We discuss future directions of how to best visualize out-of-view objects in head-mounted AR.

While HCI for development (HCI4D) research has typically focused on technological practices of poor and low-literate communities, little research has addressed how technology literate individuals living in a poor infrastructure environment use technology. Our work fills this gap by focusing on Lebanon, a country with longstanding political instability, and the wayfinding issues there stemming from missing street signs and names, a poor road infrastructure, and a non-standardized addressing system. We examine the relationship between technology literate individuals' navigation and direction giving strategies and their usage of current digital navigation aids. Drawing on an interview study (N=12) and a web survey (N=85), our findings show that while these individuals rely on mapping services and WhatsApp's share location feature to aid wayfinding, many technical and cultural problems persist that are currently resolved through social querying. We discuss our results in light of problems that any map user encounters in poor infrastructure environments.

Car navigation systems typically combine multiple output modalities; for example, GPS-based navigation aids show a real-time map, or feature spoken prompts indicating upcoming maneuvers. However, the drawback of graphical navigation displays is that drivers have to explicitly glance at them, which can distract from a situation on the road. To decrease driver distraction while driving with a navigation system, we explore the use of ambient light as a navigation aid in the car, in order to shift navigation aids to the periphery of human attention. We investigated this by conducting studies in a driving simulator, where we found that drivers spent significantly less time glancing at the ambient light navigation aid than on a GUI navigation display. Moreover, ambient light-based navigation was perceived to be easy to use and understand, and preferred over traditional GUI navigation displays. We discuss the implications of these outcomes on automotive personal navigation devices.

This paper presents the motivation, design and evaluation of CountMeIn, a mobile collaborative pervasive memory game to revive social interactions in public places (e.g. a train station or bus stop). Two versions of CountMeIn were tested; an NFC-based and a touchscreen version. In a 2×1 within-subject (NFC vs. Touch) experiment (N = 20), postexperiment group interviews and findings indicate the NFC version led to increased perception of social presence while participants were more aware of others' actions and intentions (mode of co-presence). However, we did not find quantitative evidence that attributes of social presence were higher from the Social Presence Game Questionnaire. Together, our findings suggest that placement of a physical NFC interface does not necessarily increase perceived social presence when users play collaboratively. However, social expansion in mobile collaborative pervasive games can greatly benefit from people's mutual awareness from such an interface. This mutual awareness has the potential to both attract users and spectators, and reduce anxiety of users to invite spectators, or accept an invite from users.

Urban mobility analysis of geotagged photos can unlock mobility patterns of users who took these photos, which can be used for exploration-based city route planners. Applying sequence alignment techniques on 5 years of geotagged Flickr photos in Amsterdam (The Netherlands) allowed creating walkable city routes based on paths traversed by multiple photographers (or photographer paths). To evaluate our approach, we conducted a user study with Amsterdam residents to compare our routes with the most efficient and popular route variations. Drawing on experience questionnaire data, web survey responses, and user interviews, our results show that our photographer paths were perceived as most stimulating and suitable for city exploration. Moreover, while digital aids based on photographer paths can potentially aid city exploration, their acceptance in mainstream route planners likely depends on their visualization. From our proof-of-concept approach and user study findings, we discuss the potential of data-driven exploration-based city route planners.

This paper presents the motivation, design, and pilot evaluation of CountMeIn, a pervasive collaborative game to improve the waiting time experience (e.g., waiting for a train, or traffic light to turn green). We tested two versions of CountMeIn, an NFC-based and touchscreen version in a small pilot study. Our early results showed that the NFC-based version increases collaboration, and was overall more positively perceived than the touchscreen version. We discuss the challenges ahead in deploying CountMeIn in a real-world setting.

While gesture taxonomies provide a classification of device-based gestures in terms of communicative intent, little work has addressed the usability differences in manually performing these gestures. In this primarily qualitative study, we investigate how two sets of iconic gestures that vary in familiarity, mimetic and alphabetic, are affected under varying failed recognition error rates (0-20%, 20-40%, 40-60%). Drawing on experiment logs, video observations, subjects' feedback, and a subjective workload assessment questionnaire, results revealed two main findings: a) mimetic gestures tend to evolve into diverse variations (within the activities they mimic) under high error rates, while alphabet gestures tend to become more rigid and structured and b) mimetic gestures were tolerated under recognition error rates of up to 40%, while alphabet gestures incur significant overall workload with up to only 20% error rates. Thus, while alphabet gestures are more robust to recognition errors in keeping their signature, mimetic gestures are more robust to recognition errors from a usability and user experience standpoint, and thus better suited for inclusion into mainstream device-based gesture interaction with mobile phones.

This paper describes a field study evaluating a mobile map application for the Paris Air Show. The aim of the study was to investigate how well users can navigate (to static and moving targets) and orient themselves in a fair (an unknown environment posing realistic challenges for wayfinding) with a mobile map system. The study involved 14 fair visitors who carried out three navigation tasks, which required them to switch between map navigation and deciding upon their orientation in the physical environment. Our results indicate that navigation and orientation are not as tightly coupled as described in the traditional wayfinding literature and may require different modality approaches to optimally support users. Based on this, we draw design implications on how to balance supporting the user in navigation and orientation with mobile systems without diminishing users' awareness of their surroundings.