Large Language Model-powered conversational agents (CAs) are increasingly capable of projecting sophisticated personalities through language, but how these projections affect users is unclear. We thus examine how CA personalities expressed linguistically affect user decisions and perceptions in the context of charitable giving. In a crowdsourced study, 360 participants interacted with one of eight CAs, each projecting a personality composed of three linguistic aspects: attitude (optimistic/pessimistic), authority (authoritative/submissive), and reasoning (emotional/rational). While the CA’s composite personality did not affect participants’ decisions, it did affect their perceptions and emotional responses. Particularly, participants interacting with pessimistic CAs felt lower emotional state and lower affinity towards the cause, perceived the CA as less trustworthy and less competent, and yet tended to donate more toward the charity. Perceptions of trust, competence, and situational empathy significantly predicted donation decisions. Our findings emphasize the risks CAs pose as instruments of manipulation, subtly influencing user perceptions and decisions.

Open hardware and the need for ecologically valid measurements drive the Electroencephalography (EEG) democratization movement—EEG has been steadily transcending the boundaries of clinical research, making its way into interdisciplinary fields. In Human-Computer Interaction (HCI), EEG is used to measure cognitive workload and infer cognitive processes for building cognition-aware systems. We describe and evaluate our BCIglass prototype where EEG electrodes are embedded in the frame of a mainstream Head-Mounted Display (HMD) to create a skull-peripheral topology. We devised a lab study with 34 participants who completed seven established cognitive tasks. Then, we conducted a pilot field study with one participant to test BCIglass in everyday-life settings. Our findings demonstrate that BCIglass captures EEG activity in a manner comparable to a research-grade EEG-cap system. Our topology infers the cognitive task at hand, and the underlying cognitive process(es) by proxy, with an accuracy of ∼80% and only three electrodes at the skull periphery. Embedding EEG electrodes in lightweight HMDs represents a promising approach in the quest to achieve ubiquitous brain-computer interfacing in real-world settings.

ChatGPT and other large language models (LLMs) have proven useful in crowdsourcing tasks, where they can effectively annotate machine learning training data. However, this means that they also have the potential for misuse, specifically to automatically answer surveys. LLMs can potentially circumvent quality assurance measures, thereby threatening the integrity of methodologies that rely on crowdsourcing surveys. In this paper, we propose a mechanism to detect LLM-generated responses to surveys. The mechanism uses ''prompt injection,'' such as directions that can mislead LLMs into giving predictable responses. We evaluate our technique against a range of question scenarios, types, and positions, and find that it can reliably detect LLM-generated responses with more than 98% effectiveness. We also provide an open-source software to help survey designers use our technique to detect LLM responses. Our work is a step in ensuring that survey methodologies remain rigorous vis-a-vis LLMs.

Learning to operate a complex system, such as an agile production line, can be a daunting task. The high variability in products and frequent reconfigurations make it difficult to keep documentation up-to-date and share new knowledge amongst factory workers. We introduce CLAICA, a Continuously Learning AI Cognitive Assistant that supports workers in the aforementioned scenario. CLAICA learns from (experienced) workers, formalizes new knowledge, stores it in a knowledge base, along with contextual information, and shares it when relevant. We conducted a user study with 83 participants who performed eight knowledge exchange tasks with CLAICA, completed a survey, and provided qualitative feedback. Our results provide a deeper understanding of how prior training, context expertise, and interaction modality affect the user experience of cognitive assistants. We draw on our results to elicit design and evaluation guidelines for cognitive assistants that support knowledge exchange in fast-paced and demanding environments, such as an agile production line.

Emoji have become an essential part of modern communication, helping to convey emotions and tone quickly and concisely. Emoji used by humans and Intelligent Agents (IA) have been shown to affect people's decision making intentions, suggesting they could be used to manipulate users to follow their advice. We present a mixed-methods crowdsourcing study (N = 194) that shows that adherence to an IA's recommendation and user experience are not affected by emoji when used in a positive, collaborative way. However, we demonstrate that explanations provided by an IA do increase adherence to its recommendation.

Conversational agents (CA) occasionally fail to understand the user’s intention or respond inappropriately due to natural language complexity. These conversational breakdowns can happen because of low intent and entity prediction confidence scores. A promising repair strategy in such cases is that the CA proposes to users likely alternatives to proceed. If one of these options matches the user’s intention, the breakdown is repaired successfully. We propose that successful repairs should be followed by a learning mechanism to minimize future breakdowns. After a successful repair, the CA, user, or both can learn each other’s specific phrasing. This prevents similar phrasings from causing reoccurring breakdowns. We compared user preferences for these learning mechanisms in a scenario-based study with manufacturing workers (). Our result showed that users first prefer to share the learning burden with the CA (61.3%), followed by entirely outsourcing the learning burden to the CA (60.7%) as opposed to themselves.

A moral dilemma is a decision-making paradox without unambiguously acceptable or preferable options. This paper investigates if and how the virtual enactment of two renowned moral dilemmas---the Trolley and the Mad Bomber---influence decision-making when compared with mentally visualizing such situations. We conducted two user studies with two gender-balanced samples of 60 participants in total that compared between paper-based and virtual-reality (VR) conditions, while simulating 5 distinct scenarios for the Trolley dilemma, and 4 storyline scenarios for the Mad Bomber's dilemma. Our findings suggest that the VR enactment of moral dilemmas further fosters utilitarian decision-making, while it amplifies biases such as sparing juveniles and seeking retribution. Ultimately, we theorize that the VR enactment of renowned moral dilemmas can yield ecologically-valid data for training future Artificial Intelligence (AI) systems on ethical decision-making, and we elicit early design principles for the training of such systems.

Distractions and interruptions often disrupt mobile learners. Luckily, task resumption (memory) cues can support users in resuming a learning task. These cues can have multiple forms and designs, but their effectiveness depends heavily on their adaptation to the specific learning use case. This work explores the causes of interruptions during mobile learning and outlines designs for task resumption support. We report findings from two focus groups with HCI experts (N = 4) and users of mobile learning applications (N = 3). Finally, we discuss these findings by drawing on literature, and we derive a research agenda of currently unexplored concepts. We state limitations and open questions in the domain of task resumption support for mobile learning.

We propose to design playful solutions to help young people better understand the consequences of their use of language in a community of peers. Our system, CARE, will analyse the content of their messages and extract the emotions they are charged with, both in terms of strength (arousal) and valence (negative or positive). Their effects will be translated visually in forms suitable for the different age groups. A positive reinforcement policy will be in place where good behaviour results in awards and popularity among a restricted circle of friends. Finally a simple and cheap wearable device will be offered to young persons willing to be alerted in case they get into an aggressive mood so to raise their awareness and help control themselves better.

Winter sports like skiing and snowboarding are often group activities. Groups of skiers and snowboarders traditionally use paper maps or board-mounted larger-scale maps near ski lifts to aid decision making: which slope to take next, where to have lunch, or what hazards to avoid when going off-piste. To enrich those static maps with personal content (e.g., pictures, prior routes taken, or hazards encountered), we developed SkiAR - a wearable augmented reality system that allows groups of skiers and snowboarders to share such content on a printed panoramic resort map. The contribution of our work is twofold: (1) we developed a system that offers a novel way to review and share personal content in situ while on the slope using a resort map; (2) we report on the results from a qualitative analysis of two user studies to inform the design and validate the usability and perceived usefulness of our prototype.

This paper presents insights on driver's User Experience (UX) in terms of systematically investigating predicted experience, actual experience, and recalled experience. By conducting a three-week field study with car commuters in two countries, we studied how frustration and anger differentiate in prediction, actual experience, and recall. Our results show that commuters accurately predict their upcoming anger or frustration in a traffic congestion, however, lower their experienced frustration when being recalled. Moreover, unexpected traffic congestions (in contrast to expected ones) are prone to higher levels of anger. We further found that time of day is related to the prediction of anger, and mood is related to the prediction of frustration. With our study we provide a holistic view on commuters' everyday emotions and experiences -- not only when being on the road, but also before and after the trip.

Several mobile and social media weather apps support the incorporation of human input in increasing their coverage and accuracy of current weather conditions. This practice is also known as participatory sensing: the act of using sensors (i.e. smartphones) carried by volunteers to acquire highly localized measurements of physical phenomena. In order to assess the accuracy of such user contributed weather reports, we created an android app called Atmos that allows for the in situ collection of weather data in the form of descriptive manual input. Based on a yearlong study with Atmos deployed on the Google Play store, we investigate the ability of mobile users to both report current weather conditions accurately, and to predict future weather developments. We found that mobile users can be sufficiently accurate when reporting current conditions, though report accuracy was affected by hour of day. Users were also able to provide accurate short-term predictions, particularly for temperature and wind intensity. We also present results from an online survey that gathered data from 12 countries in order to understand the role weather plays in users' daily life, which helped us design Atmos.

With the increasing sophistication of mobile computing, a growing interest has been paid to locative media that aim at providing immersive experiences. Location aware narratives are a particular kind of locative media that aim at “telling stories that unfold in real space”. This paper presents a study that aimed at assessing an underlying hypothesis of location-aware narratives: that the coupling between the physical space and the narrative will result in increased levels of immersion in the narrative. Forty-five individuals experienced a location-aware video narrative in three locations: (a) the original location that contains physical cues from the narrative world, (b) a different location that yet portrays a similar atmosphere, and (c) a location that contains neither physical cues nor a similar atmosphere. Significant differences were found in users’ experiences with the narrative in terms of immersion in the story and mental imagery, but not with regard to feelings of presence, emotional involvement or the memorability of story elements. We reflect on these findings and the implications for the design of location-aware narratives and highlight questions for further research.