Script-Strategy Aligned Generation: Aligning LLMs with Expert-Crafted Dialogue Scripts and Therapeutic Strategies for PsychotherapyChatbots 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 psychotherapy. In this work, we explored how aligning LLMs with expert-crafted scripts can enhance psychotherapeutic chatbot performance. Our comparative Study 1 showed that LLMs aligned with expert-crafted scripts through prompting and fine-tuning significantly outperformed both pure LLMs and rule-based chatbots, achieving an effective balance between dialogue flexibility 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, SSAG demonstrated performance comparable to full script alignment, empirically supporting SSAG as an efficient approach for aligning LLMs with domain expertise. Our work advances LLM applications in psychotherapy by providing a controllable and scalable solution, reducing reliance on expert effort. It also provides a collaborative framework for domain experts and developers to efficiently build expertise-aligned chatbots, broadening access to broader context of psychotherapy.2025XSXin Sun et al.Facilitating Support and BelongingCSCW
Transparent Conversational Agents: The Impact of Capability Communication on User Behavior and Mental Model AlignmentWhen a user interacts with a conversational agent for the first time, they may not be aware of the agent's capabilities, leading to suboptimal use or interaction breakdowns. To avoid a mismatch with the actual capabilities, the agent's capabilities have to be made transparent to the user. To investigate whether communication of an agent's capabilities during interactions enhances transparency and improves the user's mental model, we conducted a user study with 56 participants. Each participant had three speech-based interactions with an agent that communicated its capabilities or an agent that did not. Our results suggest that the communication led to a change in user behavior with significantly longer utterances. However, the users' mental models of the agent's capabilities were not significantly different between the conditions. Participants were able to significantly improve their knowledge of the agent's capabilities by aligning their mental model over time in both conditions.2025MRMerle M. Reimann et al.Agent Personality & AnthropomorphismExplainable AI (XAI)Privacy by Design & User ControlCUI
Interacting Like a Girl: Considering Body Comportment in the Design of Embodied InteractionsRecently, design research has embraced more-than-human perspectives to explore the complex entanglements of our world, decentering the human subject and eliminating dualistic thinking. Despite these advances, further progress is needed to develop a future that equally considers all beings. This paper examines the impact of body comportment on the design of embodied, interactive technologies. Drawing on Iris Marion Young's essay, we argue that the assumption of a universal body standard can lead to a disconnect between a person’s intentions and their interactions with technology. We relate three modalities of body comportment---ambiguous transcendence, inhibited intentionality, and discontinuous unity---to embodied interaction. These modalities offer a perspective on how embodied being-in-the-world extends beyond physical capabilities, facilitating a pluralist view of the human body. We discuss the implications of Young's essay for research and design, reflecting on how the designer’s own 'feminine existence' may influence the spatial scope of embodied interactions.2025DSDorothé Smit et al.Full-Body Interaction & Embodied InputGender & Race Issues in HCIHuman-Nature Relationships (More-than-Human Design)DIS
Technologies Supporting Self-Reflection on Social Interactions: A Systematic ReviewAs intelligent technology and applications have become an integral part of nearly all aspects of people's daily lives, many intelligent systems have been designed to help people navigate the complex space of social interactions. One prominent strategy for such intelligent support is providing meaningful Ad Hoc Interventions (ADI), e.g., through timely notifications. An alternative is Technology-Supported Reflection (TSR), e.g., by offering information about activities in one's past for personal insights. In contrast to straight-up interventions, the aim of the latter strategy is not to directly augment human skills but instead support learning and personal growth over time. However, while TSR has seen widespread interest in applications in some areas, such as physical fitness and mental health, its use for improving human social interactions has not yet been systematically explored. Concretely, it is currently unclear 1) what forms of self-reflection systems intend to support, 2) how their different technological components (e.g., data collection, information integration) are involved in providing support, and 3) what common limitations and design challenges they face. In this article, we present the results of a systematic literature review focusing on these questions to provide a structured foundation for targeted research. Concretely, we identified and analysed a collection of 23 relevant papers, each describing a system deploying TSR to support humans with elements of social interactions. We constructed a framework with a set of features to comprehensively describe and analyze the systems that support self-reflection, including their application domains, how they fit into the existing design framework, how they facilitate learning through reflection, how adaptive they are to individual users, and how they were evaluated. Finally, we propose a direction for designing systems that support individual's social interactions through self-reflection in an adaptive manner.2025CHChenxu Hao et al.Mental Health Apps & Online Support CommunitiesUser Research Methods (Interviews, Surveys, Observation)IUI
Understanding Home Router Configuration Habits & AttitudesHome routers serve as a gateway to the Internet and configuration issues such as weak passwords can simply be introduced by users that configured them, potentially leading to severe consequences. The most critical phase in the lifecycle of a home router is perhaps the initial setup intended for users to complete. Yet, the mindset and behavior of users during this process remain under-explored. In a comprehensive online survey of 392 participants across several regions, we find that router settings and user behavior vary significantly between China and English-speaking countries, influenced by factors like IT background, age, gender, and education. A majority of participants go through the configuration of their own routers, but many also admit keeping the default settings and are not actively maintaining their router firmware up-to-date, leaving security vulnerabilities unfixed. We estimate that 91% of participant routers run with default settings, which should push router manufacturers to focus on safe defaults. Moreover, while default passwords are often changed, some participants report coping strategies. With noteworthy differences that we have observed across user backgrounds, we believe that our takeaways can shed some light on advancing the area of home network security.2025JYJunjian Ye et al.Nanjing University of Posts and TelecommunicationsPrivacy by Design & User ControlPasswords & AuthenticationPrivacy Perception & Decision-MakingCHI
Pixel Memories: Do Lifelog Summaries Fail to Enhance Memory but Offer Privacy-Aware Memory Assessments?We explore the metaphorical "daily memory pill" concept – a brief pictorial lifelog recap aimed at reviving and preserving memories. Leveraging psychological strategies, we explore the potential of such summaries to boost autobiographical memory. We developed an automated lifelogging memory prosthesis and a research protocol (Automated Memory Validation ``AMV'') for conducting privacy-aware, in-situ evaluations. We conducted a real-world lifelogging experiment for a month (n=11). We also designed a browser ``Pixel Memories’’ for browsing one-week worth of lifelogs. The results suggest that daily timelapse summaries, while not yielding significant memory augmentation effects, also do not lead to memory degradation. Participants' confidence in recalled content remains unaltered, but the study highlights the challenge of users' overestimation of memory accuracy. Our core contributions, the AMV protocol and "Pixel Memories" browser, advance our understanding of memory augmentations and offer a privacy-preserving method for evaluating future ubicomp systems.2025PEPassant ElAgroudy et al.German Research Centre for Artificial Intelligence (DFKI); RPTU KaiserslauternContext-Aware ComputingUbiquitous ComputingCHI
Back to School - Sustaining Recurring Child-Robot Educational Interactions After a Long BreakMaintaining the child-robot relationship after a significant break, such as a holiday, is an important step for developing sustainable social robots for education. We ran a four-session user study (n = 113 children) that included a nine-month break between the third and fourth session. During the study, participants practiced math with the help of a social robot math tutor. We found that social personalization is an effective strategy to better sustain the child-robot relationship than the absence of social personalization. To become reacquainted after the long break, the robot summarizes a few pieces of information it had stored about the child. This gives children a feeling of being remembered, which is a key contributor to the effectiveness of social personalization. Enabling the robot to refer to information previously shared by the child is another key contributor to social personalization. Conditional for its effectiveness, however, is that children notice these memory references. Finally, although we found that children's interest in the tutoring content is related to relationship formation, personalizing the topics did not lead to more interest in the content. It seems likely that not all of the memory information that was used to personalize the content was up-to-date or socially relevant.2024MLMike E.U. Ligthart et al.Special Education TechnologySocial Robot InteractionRobots in Education & HealthcareHRI
Design Specifications for a Social Robot Math TutorTo benefit from the social capabilities of a robot math tutor, instead of being distracted by them, a novel approach is needed where the math task and the robot's social behaviors are better intertwined. We present concrete design specifications of how children can practice math via a personal conversation with a social robot and how the robot can scaffold instructions. We evaluated the designs with a three-session experimental user study (n = 130, 8-11 y.o.). Participants got better at math over time when the robot scaffolded instructions. Furthermore, the robot felt more as a friend when it personalized the conversation.2023MLMike E.U. Ligthart et al.Collaborative Learning & Peer TeachingSocial Robot InteractionHRI
'Yes, I comply!': Motivations and Practices around Research Data Management and Reuse across Scientific FieldsAs science becomes increasingly data-intensive, the requirements for comprehensive Research Data Management (RDM) grow. This often overwhelms scientists, requiring more workload and training. The failure to conduct effective RDM leads to producing research artefacts that cannot be reproduced or reused. Past research placed high value on supporting data science workers, but focused mainly on data production, collection, processing, and sensemaking. In order to understand practices and needs of data science workers in relation to documentation, preservation, sharing, and reuse, we conducted a cross-domain study with 15 scientists and data managers from diverse scientific domains. We identified five core concepts which describe common practices in generating reproducible research artefacts: Practice, Adoption, Barriers, Education, and Impact. Based on those concepts, we introduce a stage-based model of personal RDM commitment evolution. The model can be used to drive the design of future systems that support a transition to open science. We discuss infrastructure and policy involved at the stages and transitions in the model. Our work supports designers in understanding the constraints and challenges involved in designing for reproducibility in an age of data-driven science.2020SFSebastian S. Feger et al.Data WorkCSCW
Design Patterns for an Interactive Storytelling Robot to Support Children's Engagement and AgencyIn this paper we specify and validate three interaction design patterns for an interactive storytelling experience with an autonomous social robot. The patterns enable the child to make decisions about the story by talking with the robot, reenact parts of the story together with the robot, and recording self-made sound effects. The design patterns successfully support children’s engagement and agency. A user study (N = 27, 8-10 y.o.) showed that children paid more attention to the robot, enjoyed the storytelling experience more, and could recall more about the story, when the design patterns were employed by the robot during storytelling. All three aspects are important features of engagement. Children felt more autonomous during storytelling with the design patterns and highly appreciated that the design patterns allowed them to express themselves more freely. Both aspects are important features of children’s agency. Important lessons we have learned are that reducing points of confusion and giving the children more time to make themselves heard by the robot will improve the patterns efficiency to support engagement and agency. Allowing children to pick and choose from a diverse set of stories and interaction settings would make the storytelling experience more inclusive for a broader range of children.2020MLMike E.U. Ligthart et al.Social Robot InteractionInteractive Narrative & Immersive StorytellingHRI