Trust in Large Language Model chatbots depends not only on what these systems do but also on how their behavior is governed and communicated. We present Trust Mediator, a workbench that supports service owners in authoring and assessing principle sets for LLM-driven chatbots through persona-based exploration and structured scaffolds. To examine this workflow, we use three analytic lenses—specificity, coverage, and coherence—to characterize the principles produced. In an exploratory between-subjects study, we compared manual and assisted principle authoring. Participants in both conditions viewed principles as useful for governing and assessing chatbot behavior. Assisted authoring was generally perceived as more supportive and tended to broaden coverage. Manual authoring required more effort but yielded principles that were significantly more specific. These findings highlight complementary strengths of assisted and manual pathways, illustrating the value of treating principle sets as design objects within governance workflows. Beyond their analytic role in this study, the lenses also suggest opportunities for supporting the construction and inspection of principle sets.

Robots are increasingly present in spaces inhabited by humans. From a privacy-sensitive design perspective, they present challenges, as they acquire data about their environment to act autonomously and interact with their users. This may raise privacy concerns among robot users and bystanders. To address these concerns, we propose a multi-touchpoint design enabling users and bystanders to investigate how their privacy is protected. These touchpoints include (1) embodied interaction with the robot, either directly, whenever encountering a robot, or (2) later, in a dedicated physical space, (3) interaction with a virtual AI chatbot through a web site, and (4) interaction with a human Data Protection Officer. We evaluated this design and the usefulness of the proposed touchpoints in two studies. Our findings are threefold: first, all touchpoints are useful and complement each other; second, different people have different preferences; and third, the attributes of the situation (i.e. location, busyness, contextuality and sensitivity) impact the choice of the touchpoint they would use to ask their questions.

Robots powered by Artificial Intelligence require continuous sensing to function and interact autonomously with their environment. This may create concerns for their users. Here, we describe a study in the context of an office environment equipped with autonomous delivery robots. Our study aims to understand the employees’ current comprehension of the data captured by the robots, the nature of their concerns and ways to mitigate those. We found that the employees have little knowledge about data capture and that providing such knowledge can go either way, reassuring or generating new concerns which are often contextual. We qualitatively analysed reasons for having or not having concerns. Our findings include that trust in the employer is an important factor limiting them.

Conversational Agents (CAs) employing voice as their main interaction mode produce natural language utterances with the aim of mimicking human conversations. To unveil hiccups in conversations with recommender systems, we observed users interacting with CAs. Our findings suggest that those occur as users struggle to start the session, as CAs do not appear exploratory, and as CAs remained silent after offering recommendation(s) or after reporting errors. Users enacted mental models derived from years of experience with Graphical User Interfaces, but also expected human-like characteristics such as explanations and proactivity. Anchoring on these, we designed a dialogue model for a multimodal Conversational Recommender System (CRS) mimicking humans and GUIs. We probed the state of hiccups further with a Wizard-of-Oz prototype implementing this dialogue model. Our findings suggest that participants rapidly adopted GUI mimicries, cooperated for error resolution, appreciated explainable recommendations, and provided insights to improve persisting hiccups in proactivity and navigation. Based on these, we provide implications for design to address hiccups in CRS.

When people engage in urban exploration, the tool they are most likely to use today is a mobile phone. In this paper, we present observations of users’ “home” and “away” conducted to refine our understanding of situational Point-of-Interest (POI) needs. Our findings suggest three distinct categories of situations in which users seek POI information: On-the-spot, Refining plans, and Moments of boredom. Based on the similarities and differences of these three situations in five observed underlying constraints – distance of interest, engagement threshold, ambiguity of the search, profile matching, and other imperative constraints, we derive implications for designing and ranking POIs for a Situational Recommender. To further access our concept, we designed and prototyped Situational Recommender by providing an interactional representation of the situation, and ran a Wizard-of-Oz concept validation study. Our results suggest that participants understood the concept without much effort and appreciated its usefulness.

The design and development of robots involve the essential step of selecting and testing robotic interfaces. This interface selection requires careful consideration as the robot’s physical embodiment influences and adds to the traditional interfaces’ complexities. Our paper presents a decision support design framework for the a priori selection of robotic interface that was inductively formulated from our case study of designing a robot to collaborate with employees with cognitive disabilities. Our main contribution is to provide a novel framework that outlines the interface requirements according to user, robot, tasks and environment and facilitates a structured comparison of interfaces against those requirements. The framework is assessed for its potential applicability and usefulness through a qualitative study with HRI experts. The framework is appreciated as a systematic tool that enables documentation and discussion, and identified issues inform the framework’s iteration. The themes of ownership of this process in interdisciplinary teams and its role in iteratively designing interfaces are discussed.

In this paper, we present our ongoing research on socially acceptable robot navigation for an indoor elevator sharing scenario. Informed by naturalistic observations of human elevator use, we discuss the social nuances involved in a seemingly simple activity like taking an elevator and the challenges and limitations of modeling robot behaviors based on a full human-like approach. We propose the principle of machine-like for the design of robot behavior policies that effectively accomplish tasks without being disruptive to the routines of people sharing the elevator with the robots. We explored this approach in a bodystorming session and conducted a preliminary evaluation of the resulting considerations through an online user study. Partic-ipants differentiated robots from humans for issues of proxemics and priority, and machine-like behaviors were preferred over human-like behaviors. We present our findings and discuss the advantages and limitations identified for both approaches for designing socially acceptable navigation behaviors.

Recommender systems are widely integrated into our everyday activities. These intelligent systems succeed in learning the user's profile to recommend movies, music, news and more. However, for designing context-aware recommendations, new challenges emerge in predicting the situational needs of the user. We prototyped Ambient Wanderer, our personalised and contextualised Point-of-Interest (POI) recommender system and experimented it with new locals, people who have recently relocated to a city. Our key findings include: sudden breakdowns during urban exploration, trust issues with the recommendations from people unlike them, feeling bored as the trigger to POI search, intent to find free activities, information needs on areas-of-interest beyond points-of-interest and the demand to build a new social life. For each of these needs, we present the implications to design mobile recommendations for urban exploration.

This paper describes an ethnographic study of an outsourced business process - the digitization of healthcare forms. The aim of the study was to understand how the work is currently organized, with an eye to uncovering the research challenges which need to be addressed if that work is to be crowdsourced. The findings are organised under four emergent themes: Workplace Ecology, Data Entry Skills and Knowledge, Achieving Targets and Collaborative Working. For each theme a description of how the work is undertaken in the outsourcer's Indian office locations is given, followed by the implications for crowdsourcing that work. This research is a first step in understanding how crowdsourcing might be applied to BPO activities. The paper examines features specific to form digitization - extreme distribution and form decomposition - and lightly touches on the crowdsourcing of BPO work more generally.

In this paper we compare two departments of a public administration body carrying out similar work. In one department two sections, telephony and processing, are collocated whereas in the other they are not. We demonstrate the costs of distribution, in particular how the strictly enforced division of labour and limited visibility onto the workflow of the other section causes problems when dealing with normal, natural exceptions. The setting is one of seemingly routine bureaucratic work rather than high-skilled cooperative work, thus the impact of distribution might be considered rather surprising. We argue that a key requirement for any solution is to enable practitioners on the 'shop floor' the freedom to find elegant solutions to problems.

Web 2.0 tools are penetrating into organizations after their successful adoption in the consumer domain (e.g., social networking; sharing of photos, videos, tags, or bookmarks; wiki-based editing). Some of these new tools and the collaborative processes that they support on the large scale are often referred to as Collective Intelligence (CI). The workshop brings together leading researchers and designers who are studying or developing CI tools aimed at workers in organizations. The goal is to further articulate the emerging research agenda for this new CSCW area and define new observed forms of CI in organization. Studies of communities, CI tools, and new methods are discussed.

To face ongoing global warming issues and in general to promote sustainable development, a number of tools have been developed that help people to assess the impact of their behavior on the environment. In this paper we present the Personal Assessment Tool, a system that observes print behavior and aggregates information in ways meant to promote more conscious use of the shared printing resources.

This paper argues that the design of remote help-giving systems should be grounded in articulation work and the methodical ways in which help-givers and help-seekers coordinate their problem solving activities. We provide examples from ethnographic studies of both immediate and remote help-giving to explicate what we mean by articulation work and to tease out common and characteristic methods involved in help-seeking and the giving of expert advice. We then outline how emerging technologies might best be used to support articulation work in the design and development of systems for remote troubleshooting of devices with embedded computing capabilities.

Recommender systems selectively circulate information enriched with comments and feedback based on people's experience. These systems filter information in a semi-automatic and high-quality way in order to support a community during their work or leisure practices. However recommender systems are usually separate tools that require a degree of effort to be used, both when receiving information and to insert new feedback. In this paper we present our informal experiences with the use of multiple user interfaces (interactive large screen, email, paper and PDA) as means to improve the diffusion of information through an organizational unit and to improve access to information stored within an existing recommender system

While systems supporting communities of practice in work organizations have been shown to be desirable many, if not all, are decoupled from daily work practices and tools. This hinders a wide collection of data about their activities, because of the additional effort that is required from the users. Therefore a pre-requisite for a system aiming at making visible the community activity is the non-intrusive collection of data about the activities that are carried on in a workplace. We present a range of personal document management services that support the construction of a collective memory of user print activities. We have internally tested the system and verified that it successfully provided personal benefit, thereby ensuring that the system receives sufficient usage for the shared memory to be useful. The system also successfully addressed privacy concerns and effectively provided large data sets about document related activities. Finally it provided information able to trigger new or to reinforce existing informal exchanges in communities of practice at a convenient moment; the print action.

The last decade has witnessed a growing interest in what technology can do to sustain communities. Within the Campiello project innovative information technologies have been adopted to support the dynamic exchange of experiences among people living in cities with high levels of tourism, in this way reducing the progressive diminishing of identity suffered by the local communities of these cities. The system developed has been used, for an experimental period, in a neighborhood of Venice, Italy. In the paper, we reflect on the whole Campiello experience, considering all its development phases. These reflections are organized as a set of issues that require attention, respectively, in the design and deployment of community systems, illustrated with examples from Campiello. We believe that due to the relative novelty of community systems, this type of reflection is important to inform the design of future systems such that they better fulfill their objectives and become an integral part of community practices.

Automated collaborative filtering systems collect evaluations from users of the quality and relevance of stored information items, such as scientific papers, books, and movies. A number of users need to give evaluations for the systems to be able to produce statistically high quality predictions of an item’s interest. Promoting the creation of a rich meta-layer of evaluations is essential for these systems, but several important issues remain to be resolved. The work presented here first analyses the issues around the collection of recommendations, then proposes a set of design principles for improving and automating the collection of recommendations, and finally presents how these principles have been implemented in a real usage

The debate on the language/action perspective has be!en receiving attention in the CSCW field for almost ten years. In this paper, we recall the most relevant issues raised during this debate, and propose a new exploitation of the language/action perspective by considering it from the viewpoint of understanding the complexity of communication within work processes and the situatedness of work practices. On this basis, we have defined a new conversation model, the Milan Conversation Model, and 'we are designing a new conversation handler to implement it.