Multilingual collaboration is increasingly common as today’s world becomes global and culturally diverse. While diversity fosters innovation, language barriers can hinder involvement and effective communication. Prior work has primarily focused on improving translation accuracy with limited attention to how translation systems shape dimensions of trust in interaction. Given that users must rely blindly on technology due to their inability to understand the system’s output, this issue becomes a crucial aspect. To address this gap, we introduce MorphHat, a co-embodied humanoid robot interpreter featuring a customizable, morphing face that visually represents the active speaker. We evaluated MorphHatMorphHat influenced trust, rapport, and social presence. We discuss these insights as early design implications for future embodied translation systems.

Knowledge workers increasingly rely on multi-agent systems to solve complex problems. While these systems offer valuable support, they often obscure which agents contributed to a response, leading to a lack of transparency that may result in errors and reduced trust. To address this, we propose avatars that make agents’ expertise and contributions transparent. We iteratively co-designed avatars representing distinct expertise areas and validated them in an experiment (N=100). Building on this, we developed four multi-agent prototypes varying in explanation modality (text vs. avatars) and resolution (low vs. high). We then conducted a mixed-methods evaluation with an online experiment (N=124) and follow-up interviews (N=20). Qualitative results suggest that avatars foster clearer mental models, improve perceived explainability, and support users’ trust calibration without increasing cognitive load, although no significant quantitative differences were found. Our research contributes validated avatar designs, insights into explanation strategies, and design implications for explainable multi-agent systems.

Researchers often attribute social media’s appeal to its ability to elicit flow experiences of deep absorption and effortless engagement. Yet prolonged use has also been linked to distraction, fatigue, and lower mood. This paradox remains poorly understood, in part because prior studies rely on habitual or one-shot reports that ask participants to directly attribute flow to social media. To address this gap, we conducted a five-day field study with 40 participants, combining objective smartphone app tracking with daily reconstructions of flow-inducing activities. Across 673 reported flow occurrences, participants rarely associated flow with social media (2%). Instead, heavier social media use predicted fewer daily flow occurrences. We further examine this relationship through the effects of social media use on fatigue, mood, and motivation. Altogether, our findings suggest that flow and social media may not align as closely as assumed - and might even compete - underscoring the need for further research.

Cognitive empathy, the ability to understand others‘ perspectives, is essential for effective communication, reducing biases, and constructive negotiation. However, this skill is declining in a performance-driven society, which prioritizes efficiency over perspective-taking. Here, the training of cognitive empathy is challenging because it is a subtle, hard-to-perceive soft skill. To address this, we developed CoEmpaTeam, a VR-based system that enables users to train their cognitive empathy by using LLM-driven avatars with different personalities. Through dynamic role play, users actively engage in perspective-taking, experiencing situations through another person’s eyes. CoEmpaTeam deploys three avatars who significantly differ in their personality, validated by a technical evaluation and an online experiment (n=90). Next, we evaluated the system through a lab experiment with 32 participants who performed three sessions across two weeks, followed by a one-week diary study. Our results showed a significant increase in cognitive empathy, which, according to participants, transferred into their real lives.

Immersive learning environments such as virtual classrooms in Virtual Reality (VR) offer learners unique learning experiences, yet providing effective learner support remains a challenge. While prior HCI research has explored in-lecture support for immersive learning, little research has been conducted to provide post-lecture support, despite being critical for sustained motivation, engagement, and learning outcomes. To address this, we present AttentiveLearn, a learning ecosystem that generates personalized quizzes on a mobile learning assistant based on learners’ attention distribution inferred using eye-tracking in VR lectures. We evaluated the system in a four-week field study with 36 university students attending lectures on Bayesian data analysis. AttentiveLearn improved learners’ reported motivation and engagement, without conclusive evidence of learning gains. Meanwhile, anecdotal evidence suggested improvements in attention for certain participants over time. Based on our findings of the field study, we provide empirical insights and design implications for personalized post-lecture support for immersive learning systems.

Public access to information through open data is critical for achieving the United Nations’ Sustainable Development Goal 16, which promotes accountable and inclusive institutions. However, open data portals often present barriers, such as complex user interfaces and large data catalogs, that hinder non-technical users from effectively accessing and interpreting the data. To address this problem, we conducted a two-cycle design science research project, guided by the theory of effective use, to design an explainable large language model (LLM)-based open data assistant. After focusing on transparent interaction in the initial design cycle, we evaluated our final artifact through a large-scale online experiment with 223 U.S. citizens using official Texas open data. Our results suggest that while the assistant’s use of natural language enables intuitive access, supplementing answers with explanations of the reasoning process improves citizens’ representational fidelity and effectiveness in finding information. Unexpectedly, we also find that providing a traditional data catalog alongside the conversational interface reduced representational fidelity, suggesting that direct access to raw data may overwhelm citizens. Furthermore, the results show that our design increases perceived government transparency and trust, demonstrating its broader social impact. We synthesize these findings into two design principles for explainable LLM-based open data assistants. Our research contributes to the literature by offering valuable design knowledge for explainable LLM-based systems and by adding novel insights to the discussion about democratizing access to open data. Additionally, we provide practical guidance for implementing LLM-based open data assistants that empower citizens to hold government institutions accountable.

Abstract Labeling is critical in creating training datasets for supervised machine learning, and is a common form of crowd work heteromation. It typically requires manual labor, is badly compensated and not infrequently bores the workers involved. Although task variety is known to drive human autonomy and intrinsic motivation, there is little research in this regard in the labeling context. Against this backdrop, we manipulate the presentation sequence of a labeling task in an online experiment and use the theoretical lens of self-determination theory to explain psychological work outcomes and work performance. We rely on 176 crowd workers contributing with group comparisons between three presentation sequences (by label, by image, random) and a mediation path analysis along the phenomena studied. Surprising among our key findings is that the task variety when sorting by label is perceived higher than when sorting by image and the random group. Naturally, one would assume that the random group would be perceived as most varied. We choose a visual metaphor to explain this phenomenon, whereas paintings offer a structured presentation of coloured pixels, as opposed to random noise.

Accessibility support in prototyping tools remains fragmented, despite increasing regulatory demands and well-established guidelines.Current accessibility support in prototyping tools primarily addresses visual issues such as color contrast or touch target size, leaving large gaps for issues requiring semantic understanding.

Figure 1: GUI prototype (1) and three views (2-4) of our assistant for GUI prototype designers integrated as a plug-in into a prototyping tool.Our assistant displays user stories (2) imported from collaboration tools (e.g., JIRA) for prototype designers to reference while working.It detects whether a user story is implemented (3, 4), identifies relevant GUI components (3), and generates GUI components for user stories (4). Figure uses Google Material 3 Design Kit [24] components under CC BY 4.0.

Graphical User Interface (GUI) prototyping is a fundamental component in the development of modern interactive systems, which are now ubiquitous across diverse application domains. GUI prototypes play a critical role in requirements elicitation by enabling stakeholders to visualize, assess, and refine system concepts collaboratively. Moreover, prototypes serve as effective tools for early testing, iterative evaluation, and validation of design ideas with both end users and development teams. Despite these advantages, the process of constructing GUI prototypes remains resource-intensive and time-consuming, frequently demanding substantial effort and expertise. Recent research has sought to alleviate this burden through natural language (NL)-based GUI retrieval approaches, which typically rely on embedding-based retrieval or tailored ranking models for specific GUI repositories. However, these methods often suffer from limited retrieval performance and struggle to generalize across arbitrary GUI datasets. In this work, we present GUI-ReRank, a novel framework that integrates rapid embedding-based constrained retrieval models with highly effective multi-modal (M)LLM-based reranking techniques. GUI-ReRank further introduces a fully customizable GUI repository annotation and embedding pipeline, enabling users to effortlessly make their own GUI repositories searchable, which allows for rapid discovery of relevant GUIs for inspiration or seamless integration into customized LLM-based retrieval-augmented generation (RAG) workflows. We evaluated our approach on an established NL-based GUI retrieval benchmark, demonstrating that GUI-ReRank significantly outperforms state-of-the-art (SOTA) tailored Learning-to-Rank (LTR) models in both retrieval accuracy and generalizability. Additionally, we conducted a comprehensive cost and efficiency analysis of employing MLLMs for reranking, providing valuable insights regarding the trade-offs between retrieval effectiveness and computational resources. Video presentation of GUI-ReRank available at: https://youtu.be/7x9UCh82ug

In today’s data-driven world, enterprises face the dual challenge of deriving value from vast datasets and effectively communicating insights. While data storytelling is integral for conveying insights, existing authoring tools often fail to fully leverage domain expertise or support the entire storytelling process. This paper introduces StoryPoint, an open-source data story authoring tool that combines domain expertise with Generative AI to dynamically enhance data story creation. We found that enabling domain experts to intuitively visualize data via natural language inputs, supported by automatically generated charts and narratives, helps narrow the gap between visualization and interpretation. To design StoryPoint, we followed a literature-grounded and user-centered design approach. A formative evaluation with eight domain experts reveals StoryPoint’s efficacy in rapid data story prototyping. A summative evaluation, including (i) a small-scale experiment comparing StoryPoint with a benchmark, (ii) a large-scale online experiment with 104 crowdworkers, and (iii) three real-world industry cases, underscores its utility. Our findings highlight that StoryPoint reduces data story creation time by more than 50% compared to the benchmark, receives significantly higher usability ratings, and supports the creation of data stories rating higher in readability, fluency, clarity, and trustworthiness. • StoryPoint - first open-source data story authoring tool for enterprises. • Combining LLMs with domain expertise enhances enterprise data storytelling workflows. • Empirical evaluations with domain experts and real-world use cases demonstrate StoryPoint’s efficiency, usability, and ability to create high-quality data stories. • Evaluation scales for assessing narrative elements and data story quality in enterprise contexts.

Mixed Reality (MR) has demonstrated its potential in various learning contexts. MR-based learning environments empower users to actively explore learning content visualized in multiple formats, such as 3D models, videos, and images. Nonetheless, the sophisticated visualizations in MR learning environments may result in potential visual overload, posing a challenge for users in efficiently allocating their attention. In this paper, we present AF-Mix, a learning support system that leverages eye tracking sensors in Microsoft HoloLens 2 to offer attention feedback for learners. Aiming to design AF-Mix, we conducted a participatory design study and integrated the attention feedback into our system, following users’ needs and suggestions. Furthermore, we evaluated AF-Mix in an evaluation study (n = 22) following a quantitative analysis of users’ visual behavior, as well as a qualitative analysis of interview transcripts. Our findings show that providing feedback to support the learning process can be achieved effectively with eye tracking. In specific, attention feedback assists learners in retrieving previously missed information and encourages learners to reallocate their attention in the review process. Moreover, providing personalized feedback based on previous attention allocation is more effective in supporting users than a self-review approach without gaze-aware assistance in MR. Such feedback facilitates users in managing their limited attentional resources better and supports the reflection of their learning journey more effectively. • Human-centered design of attention feedback in Mixed Reality (MR) learning systems. • Evaluation of the system using qualitative and quantitative methods. • Attention feedback in MR supports users in attention management and self-reflection. • Design recommendations for supporting self-reflection in MR learning systems.

In recent years, the availability of easy-to-use prototyping tools has empowered designers to create GUI designs. In parallel, a broad spectrum of usability testing tools have been proposed to support the collection of quantitative test data from crowd-testers. However, test specification and results are typically disconnected from created GUI designs and, therefore, difficult to translate into improvements. In this paper, we present TESY, a prototyping assistant integrating usability test specification and resulting test data. We implement TESY as a plug-in in the prototyping tool Figma. In a controlled lab study, we compare how 34 untrained designers create prototypes, specify usability tests, and improve the prototypes using the collected test data with and without TESY. We contribute by demonstrating how TESY empowers untrained designers to create enhanced GUI designs following a usability test-driven prototyping approach. Specifically, we demonstrate how TESY's capability of tightly integrating test data provided by crowd-testers into the prototyping tool leads to more data-driven and task-focused design improvements.

Users can adapt contemporary natural language interfaces (NLIs) by teaching the NLIs how to handle new natural language (NL) inputs. One promising approach is interactive task learning (ITL), which enables users to teach new NL inputs for multi-modal systems. While recent advances enable users to teach the syntactic and semantic level of the NL inputs through ITL, NLIs are still not able to learn how to consider the context, such as the current state of the graphical user interface (GUI). To address this challenge, we designed MALACHITE through three formative studies. MALACHITE enables users to successfully teach NL inputs on a semantic and syntactic level leveraging the GUI screen of a data visualization tool. With two evaluative studies, we provide evidence that with MALACHITE ’s suggestions, users significantly improve their accuracy by a factor of 2.3 in teaching GUI-dependent NL inputs in contrast to those without MALACHITE ’s suggestions.

Large language models (LLMs) are prone to hallucinations, i.e., nonsensical, unfaithful, and undesirable text. Users tend to overrely on LLMs and corresponding hallucinations which can lead to misinterpretations and errors. To tackle the problem of overreliance, we propose HILL, the "Hallucination Identifier for Large Language Models". First, we identified design features for HILL with a Wizard of Oz approach with nine participants. Subsequently, we implemented HILL based on the identified design features and evaluated HILL’s interface design by surveying 17 participants. Further, we investigated HILL’s functionality to identify hallucinations based on an existing question-answering dataset and five user interviews. We find that HILL can correctly identify and highlight hallucinations in LLM responses which enables users to handle LLM responses with more caution. With that, we propose an easy-to-implement adaptation to existing LLMs and demonstrate the relevance of user-centered designs of AI artifacts.

This paper explores the impact of generative ar-tificial intelligence on text production, focusing on the use of prompt-based AI tools. We propose to move beyond the current use of Large Language Models (LLMs) as “ghostwriters” and advocate for their relevance as tools to enhance the development of epistemic-heuristic strategies to facilitate knowledge construction. Our planned study aims to gain insight into the cognitive processes and behavior of university students when interacting with content generated by LLMs using eye tracking technology. Based on these insights, we explore the potential of providing cognition-aware assistance to enhance writing skills in educational contexts.

Interactive systems are omnipresent today and the need to create graphical user interfaces (GUIs) is just as ubiq-uitous. For the elicitation and validation of requirements, GUI prototyping is a well-known and effective technique, typically employed after gathering initial user requirements represented in natural language (NL) (e.g., in the form of user stories). Un-fortunately, G UI prototyping often requires extensive resources, resulting in a costly and time-consuming process. Despite various easy-to-use prototyping tools in practice, there is often a lack of adequate resources for developing G UI prototypes based on given user requirements. In this work, we present a novel Large Language Model (LLM)-based approach providing assistance for validating the implementation of functional NL- based require-ments in a GUI prototype embedded in a prototyping tool. In particular, our approach aims to detect functional user stories that are not implemented in a G UI prototype and provides recommendations for suitable GUI components directly imple-menting the requirements. We collected requirements for existing GUIs in the form of user stories and evaluated our proposed validation and recommendation approach with this dataset. The obtained results are promising for user story validation and we demonstrate feasibility for the GUI component recommendations.

In today’s work and life, the use of video meeting systems is ubiquitous. As usage continues to rise, the negative effects of video meeting systems on users have become apparent. Consequently, scholars and public media have called for a better comprehension of the impact of video meeting systems on users with respect to psychological user states and ensuing outcomes. However, a synopsis of existing empirically grounded knowledge in this field is non-existent. To fill this gap, we review existing literature with a focus on psychological user states from a cognitive and affective perspective as well as downstream outcomes. Specifically, we review and conceptualize findings from 78 quantitative studies and describe the results in a morphological box. We identified a focus on examining the overall systems’ impact on the user states of attention, awareness, and negative emotions. Moreover, there has been a rise in literature examining recently developed features that concentrate on supporting attention and emotion understanding. Besides, video meeting systems have been predominantly explored in the context of generic conversations in work settings. By providing future research directions, this overview offers scholars the potential to design their studies more effectively and informs designers to facilitate system improvements based on empirical findings.

Video meeting systems offer great potential for work and life, but they can also have negative effects. One reason is the presence of technical stimuli that do not exist in the physical world. A prominent example is the self-view feature, a mirrored image of oneself shown during the video meeting. The self-view feature comes with a trade-off between the advantage of enhancing control and the disadvantage of increasing cognitive load of its users. So far, research is scarce when it comes to understanding this ambivalent nature and studies mostly relied on self-reported data without considering the actual interaction with the self-view. To address this gap, we conducted an experimental study with 57 participants and two design variants (with/without self-view), analyzed user perceptions through surveys and interviews, and explored gaze patterns using eye-tracking technology. Results reveal varying perceptions of cognitive load and control among self-view users and between the design variants, highlighting its ambivalent nature. We see differences in how participants interact with the self-view. In a cluster analysis, we identify three user groups (Benefiting Users, Cognitively Challenged Users, Control Losing Users). These groups also show differences in visual behavior, especially median fixation duration, and user characteristics. Based on our findings, we outline design recommendations for more flexible and intelligent design solutions by considering user groups and their individual differences.

Crowd feedback overcomes scalability issues of feedback collection on interactive website designs. However, collecting feedback on crowdsourcing platforms decouples the feedback provider from the context of use. This creates more effort for crowdworkers to immerse into such context in crowdsourcing tasks. In this paper, we present CrowdSurfer, a browser extension that seamlessly integrates design feedback collection in crowdworkers’ everyday internet surfing. This enables the scalable collection of in situ feedback and, in parallel, allows crowdworkers to flexibly integrate their work into their daily activities. In a field study, we compare the CrowdSurfer against traditional feedback collection. Our qualitative and quantitative results reveal that, while in situ feedback with the CrowdSurfer is not necessarily better, crowdworkers appreciate the effortless, enjoyable, and innovative method to conduct feedback tasks. We contribute with our findings on in situ feedback collection and provide recommendations for the integration of crowdworking tasks in everyday internet surfing.

Users are increasingly empowered to personalize natural language interfaces (NLIs) by teaching how to handle new natural language (NL) inputs. However, our formative study found that when teaching new NL inputs, users require assistance in clarifying ambiguities that arise and want insight into which parts of the input the NLI understands. In this paper we introduce ONYX, an intelligent agent that interactively learns new NL inputs by combining NL programming and programming-by-demonstration, also known as multi-modal interactive task learning. To address the aforementioned challenges, ONYX provides suggestions on how ONYX could handle new NL inputs based on previously learned concepts or user-defined procedures, and poses follow-up questions to clarify ambiguities in user demonstrations, using visual and textual aids to clarify the connections. Our evaluation shows that users provided with ONYX’s new features achieved significantly higher accuracy in teaching new NL inputs (median: 93.3%) in contrast to those without (median: 73.3%).

Intelligent writing assistants use artificial intelligence to support the partial automation of the writing process. Existing research has investigated the interaction between humans and automated systems and has identified the maintenance of situation awareness (SA) as a key challenge for humans. Especially in the context of intelligent writing assistants, humans have to maintain SA as they are held responsible for the written text. Eye tracking is the key technology that enables the non-invasive detection of situation awareness based on eye movements. Building on existing research on human-robot/AI collaboration and their interplay with SA theory, we propose the augmentation of human interaction with intelligent writing assistants through the use of eye tracking technology. On this basis, writing assistants can be adapted to users’ cognitive states such as SA. We argue that for the successful implementation of intelligent writing assistants in the real world, eye-based analysis of SA and augmentation are key.

Leveraging crowdsourcing in software development has received growing attention in research and practice. Crowd feedback offers a scalable and flexible way to evaluate software design solutions and the potential of crowd-feedback systems has been demonstrated in different contexts by existing research studies. However, previous research lacks a deep understanding of the effects of individual design features of crowd-feedback systems on feedback quality and quantity. Additionally, existing studies primarily focused on understanding the requirements of feedback requesters but have not fully explored the qualitative perspectives of crowd-based feedback providers. In this paper, we address these research gaps with two research studies. In study 1, we conducted a feature analysis (N=10) and concluded that from a user perspective, a crowd-feedback system should have five core features (scenario, speech-to-text, markers, categories, and star rating). In the second study, we analyzed the effects of the design features on crowdworkers' perceptions and feedback outcomes (N=210). We learned that offering feedback providers scenarios as the context of use is perceived as most important. Regarding the resulting feedback quality, we discovered that more features are not always better as overwhelming feedback providers might decrease feedback quality. Offering feedback providers categories as inspiration can increase the feedback quantity. With our work, we contribute to research on crowd-feedback systems by aligning crowdworker perspectives and feedback outcomes and thereby making the software evaluation not only more scalable but also more human-centered.

The focal role of flow in promoting desirable outcomes in companies, such as increased employees’ well-being and performance, led scholars to study flow in the context of work. However, current measurement approaches which assess flow via self-report scales after task execution are limited due to obtrusiveness and a lack of real-time support. Hence, new measurement approaches must be created to overcome these limitations. In this article, we use cardiac features (heart rate variability; HRV) and a Random Forest classifier to distinguish high and low flow. Our results from a large-scale lab experiment with 158 participants and a field study with nine participants reveal, that with HRV features alone, flow-classifiers can be built with an accuracy of 68.5 percent (lab) and 70.6 percent (field). Our research contributes to the challenge of developing a less obtrusive, real-time measurement method of flow based on physiological features and to investigate flow from a physiological perspective. Our findings may serve as foundation for future work aiming to build physio-adaptive systems which can improve employee's performance. For instance, these systems could ensure that no notifications are forwarded to employees when they are ‘sensing’ flow.

In Explainable Artificial Intelligence (XAI) research, various local model-agnostic methods have been proposed to explain individual predictions to users in order to increase the transparency of the underlying Artificial Intelligence (AI) systems. However, the user perspective has received less attention in XAI research, leading to a (1) lack of involvement of users in the design process of local model-agnostic explanations representations and (2) a limited understanding of how users visually attend them. Against this backdrop, we refined representations of local explanations from four well-established model-agnostic XAI methods in an iterative design process with users. Moreover, we evaluated the refined explanation representations in a laboratory experiment using eye-tracking technology as well as self-reports and interviews. Our results show that users do not necessarily prefer simple explanations and that their individual characteristics, such as gender and previous experience with AI systems, strongly influence their preferences. In addition, users find that some explanations are only useful in certain scenarios making the selection of an appropriate explanation highly dependent on context. With our work, we contribute to ongoing research to improve transparency in AI.

Surveys are a widely used method for data collection from participants. However, responding to surveys is a time consuming task and requires cognitive and physical efforts of the participants. Eye-based interactions offer the advantage of high speed pointing, low physical effort and implicitness. These advantages are already successfully leveraged in different domains, but so far not investigated in supporting participants in responding to surveys. In this paper, we present EyeLikert, a tool that enables users to answer Likert-scale questions in surveys with their eyes. EyeLikert integrates three different eye-based interactions considering the Midas Touch problem. We hypothesize that enabling eye-based interactions to fill out surveys offers the potential to reduce the physical effort, increase the speed of responding questions, and thereby reduce drop-out rates.

Structured Visual Content (SVC) such as graphs, flow charts, or the like are used by authors to illustrate various concepts. While such depictions allow the average reader to better understand the contents, images containing SVCs are typically not machine-readable. This, in turn, not only hinders automated knowledge aggregation, but also the perception of displayed information for visually impaired people. In this work, we propose a synthetic dataset, containing SVCs in the form of images as well as ground truths. We show the usage of this dataset by an application that automatically extracts a graph representation from an SVC image. This is done by training a model via common supervised learning methods. As there currently exist no large-scale public datasets for the detailed analysis of SVC, we propose the Synthetic SVC (SSVC) dataset comprising 12,000 images with respective bounding box annotations and detailed graph representations. Our dataset enables the development of strong models for the interpretation of SVCs while skipping the time-consuming dense data annotation.We evaluate our model on both synthetic and manually annotated data and show the transferability of synthetic to real via various metrics, given the presented application. Here, we evaluate that this proof of concept is possible to some extend and lay down a solid baseline for this task. We discuss the limitations of our approach for further improvements. Our utilized metrics can be used as a tool for future comparisons in this domain. To enable further research on this task, the dataset is publicly available at https://bit.ly/3jN1pJJ.

Video-meetings essentially determine remote work life. However, video-meetings experience challenges originating from human emotions. Therefore, emotional competence, the ability to perceive, understand, and regulate emotions, is of the highest relevance. With limited transfer capacity of emotional information and various communication challenges, developing emotional competence, however, is complex. To overcome this complexity, we present TeamSpiritous, an individual, retrospective emotional competence development system for video-meetings. TeamSpiritous allows to upload and analyze recorded video-meetings on emotional processes and provides support for individual development of emotional competence. We evaluated TeamSpiritous quantitatively and qualitatively in a six-week, longitudinal field study with 47 participants from China and Germany. Results of our study show that intra- and interpersonal emotional competence significantly increased over time for the whole sample. In particular, intrapersonal emotion regulation and interpersonal emotion perception and understanding improved. Since remote work video-meetings are often multicultural, we also investigated cultural differences and observed in our results that the effects of TeamSpiritous exist beyond cultural backgrounds (China, Germany). With our work, we contribute with the design of TeamSpiritous and understanding of its effects on emotional competence development.

User input is essential for the successful development of question-and-answer (QA) chatbots. Therefore, interactive development systems are emerging that allow developers to involve test-users in the QA chatbot development process. Although the feasibility and effectiveness of this approach have been demonstrated, there is a lack of knowledge on how to design interactive QA chatbot development systems to increase test-user engagement as well as data quality in this time-consuming and tedious task. To address this research gap, we propose an interactive system design based on the interactivity effects model. We instantiate the proposed design and introduce Intrance, an interactive enhancement system for QA chatbots. Subsequently, we show in two online experiments that the proposed design significantly increases subjective and objective engagement of test-users and has a positive effect on data quality, conceptualized as data completeness and data accuracy. We discuss design implications for an implementation of the proposed design in commercial chatbot development systems.

Qualitative research can produce a rich understanding of a phenomenon but requires an essential and strenuous data annotation process known as coding. Coding can be repetitive and time-consuming, particularly for large datasets. Existing AI-based approaches for partially automating coding, like supervised machine learning (ML) or explicit knowledge represented in code rules, require high technical literacy and lack transparency. Further, little is known about the interaction of researchers with AI-based coding assistance. We introduce Cody, an AI-based system that semi-automates coding through code rules and supervised ML. Cody supports researchers with interactively (re)defining code rules and uses ML to extend coding to unseen data. In two studies with qualitative researchers, we found that (1) code rules provide structure and transparency, (2) explanations are commonly desired but rarely used, (3) suggestions benefit coding quality rather than coding speed, increasing the intercoder reliability, calculated with Krippendorff’s Alpha, from 0.085 (MAXQDA) to 0.33 (Cody).

Software development process ambidexterity (SDPA) is the ability to demonstrate both process alignment and process adaptability simultaneously. Realizing process ambidexterity has recently been suggested as an effective approach to improving the performance of software development (SD) projects. To understand the mechanisms underlying the effects of ambidexterity, we focus in this study on the mediating effects of coordination, one of the most important activity in SD projects. Specifically, we hypothesize a mediating effect of coordination costs and coordination effectiveness on the relationship between SDPA and project performance. We conducted a quantitative study involving 104 SD projects across 10 firms to test the model. The results strongly suggest that the positive relationship between SDPA and project performance is negatively mediated by coordination costs and positively mediated by coordination effectiveness. We validate our research model with a case study in an organization employing several hundred IT professionals and derive several practical implications on this basis.

Digital services are a key driver of contemporary businesses. In order to scale the implementation of design-centric development processes, companies increasingly assign design work to design novices. As design novices have limited design knowledge and experience, they are challenged to select adequate design techniques throughout the entire lifecycle of digital services. Thus, providing decision aids to design novices is becoming increasingly important. In this research, we investigate taxonomy-based and tags-based decision aids. We draw on cognitive fit theory to construct a research model explaining the relationship between different decision aids and selection accuracy while considering the cognitive effort and the decision styles of novice designers. To test our hypotheses, we conducted a between-subject laboratory experiment with 195 subjects. Our experimental results provide extensive support to our hypotheses. Taxonomy-based decision aids outperform tags-based decision aids concerning selection accuracy mediated by cognitive effort. Furthermore, the results suggest rational decision style as a moderator in the relationship between taxonomy-based decision aids and selection accuracy. Our results have practical implications: First, taxonomy-based decision aids should be primarily leveraged on decision support platforms supporting design processes. Second, design novices' decision style and cognitive effort are influential factors when developing decision aids to support digital service design processes.

Fueled by the pervasion of tools like Slack or Microsoft Teams, the usage of text-based communication in distributed teams has grown massively in organizations. This brings distributed teams many advantages, however, a critical shortcoming in these setups is the decreased ability of perceiving, understanding and regulating emotions. This is problematic because better team members? abilities of emotion management positively impact team-level outcomes like team cohesion and team performance, while poor abilities diminish communication flow and well-being. Leveraging chatbot technology in distributed teams has been recognized as a promising approach to reintroduce and improve upon these abilities. In this article we present three chatbot designs for emotion management for distributed teams. In order to develop these designs, we conducted three participatory design workshops which resulted in 153 sketches. Subsequently, we evaluated the designs following an exploratory evaluation with 27 participants. Results show general stimulating effects on emotion awareness and communication efficiency. Further, they report emotion regulation and increased compromise facilitation through social and interactive design features, but also perceived threats like loss of control. With some design features adversely impacting emotion management, we highlight design implications and discuss chatbot design recommendations for enhancing emotion management in teams.

Context: Digital transformation impacts an ever-increasing amount of everyone's business and private life. It is imperative to incorporate user requirements in the development process to design successful information systems (IS). Hence, requirements elicitation (RE) is increasingly performed by users that are novices at contributing requirements to IS development projects. Objective: We need to develop RE systems that are capable of assisting a wide audience of users in communicating their needs and requirements. Prominent methods, such as elicitation interviews, are challenging to apply in such a context, as time and location constraints limit potential audiences. Research Method: We present the prototypical self-elicitation system "LadderBot". A conversational agent (CA) enables end-users to articulate needs and requirements on the grounds of the laddering method. The CA mimics a human (expert) interviewer's capability to rephrase questions and provide assistance in the process. An experimental study is proposed to evaluate LadderBot against an established questionnaire-based laddering approach. Contribution: This work-in-progress introduces the chatbot LadderBot as a tool to guide novice users during requirements self-elicitation using the laddering technique. Furthermore, we present the design of an experimental study and outline the next steps and a vision for the future.

Interruptions are known as one of the big challenges in working environments. Due to improper resuming the primary task, such interruptions may result in task resumption failures and negatively influence the task performance. This phenomenon also occurs when users are working with information dashboards in working environments. To address this problem, an attentive dashboard issuing visual feedback is developed. This feedback supports the user in resuming the primary task after the interruption by guiding the visual attention. The attentive dashboard captures visual attention allocation of the user with a low-cost screen-based eye-tracker while they are monitoring the graphs. This dashboard is sensitive to the occurrence of external interruption by tracking the eye-movement data in real-time. Moreover, based on the collected eye-movement data, two types of visual feedback are designed which highlight the last fixated graph and unnoticed ones.

Organizations deploy gamification in CSCW systems to enhance motivation and behavioral outcomes of users. However, gamification approaches often cause competition between users, which might be inappropriate for working environments that seek cooperation. Drawing on the social interdependence theory, this paper provides a classification for gamification features and insights about the design of cooperative gamification. Using the example of an innova-tion community of a German engineering company, we present the design of a cooperative gamification approach and results from a first experimental evaluation. The findings indicate that the developed gamification approach has positive effects on perceived enjoyment and the intention towards knowledge sharing in the considered innovation community. Besides our conceptual contribu-tion, our findings suggest that cooperative gamification may be beneficial for cooperative working environments and represents a promising field for future research.

In this paper we present an approach to model ontology evolution as reconfiguration-design problem solving. The problem is reduced to a graph search where the nodes are evolving ontologies and the edges represent the changes that transform the source node into the target node. The search is guided by the constraints provided partially by a user and partially by a set of rules defining ontology consistency. In this way we allow a user to specify an arbitrary request declaratively and ensure its resolving. The approach is implemented in the KAON framework and the evaluation study shows its benefits.

The vision of the Semantic Web can only be realized through proliferation of well-known ontologies describing different domains. To enable interoperability in the Semantic Web, it will be necessary to break these ontologies down into smaller, well-focused units that may be reused. Currently, three problems arise in that scenario. Firstly, it is difficult to locate ontologies to be reused, thus leading to many ontologies modeling the same thing. Secondly, current tools do not provide means for reusing existing ontologies while building new ontologies. Finally, ontologies are rarely static, but are being adapted to changing requirements. Hence, an infrastructure for management of ontology changes, taking into account dependencies between ontologies is needed. In this paper we present such an infrastructure addressing the aforementioned problems.

Text clustering typically involves clustering in a high dimensional space, which appears difficult with regard to virtually all practical settings. In addition, given a particular clustering result it is typically very hard to come up with a good explanation of why the text clusters have been constructed the way they are. We propose a new approach for applying background knowledge (in terms of an ontology) during preprocessing in order to improve clustering results and allow for selection between results. The results may be distinguished and explained by the corresponding selection of concepts in the ontology. Our results compare favourably with a sophisticated baseline preprocessing strategy.

Richly interlinked, machine-understandable data constitutes the basis for the Semantic Web. Annotating web documents is one of the major techniques for creating metadata on the Web. However, annotation tools so far are restricted in their capabilities of providing richly interlinked and truely machine-understandable data. They basically allow the user to annotate with plain text according to a template structure, such as Dublin Core. We here present CREAM (Creating RElational, Annotation-based Metadata), a framework for an annotation environment that allows to construct relational metadata, i.e. metadata that comprises class instances and relationship instances. These instances are not based on a fix structure, but on a domain ontology. We discuss some of the requirements one has to meet when developing such a framework, e.g. the integration of a metadata crawler, inference services, document management and information extraction, and describe its implementation, viz. Ont-O-Mat a component-based, ontology-driven annotation tool.

The core idea of the Semantic Web is to make information accessible to human and software agents on a semantic basis. Hence, Web sites may feed directly from the Semantic Web exploiting the underlying structures for human and machine access. We have developed a domain-independent approach for developing semantic portals, viz. SEAL (SEmantic portAL), that exploits semantics for providing and accessing information at a portal as well as constructing and maintaining the portal. In this paper we focus on semantics-based means that make semantic Web sites accessible from the outside, i.e. semantics-based browsing, semantic querying, querying with semantic similarity, and machine access to semantic information. In particular, we focus on methods for acquiring and structuring community information as well as methods for sharing information.As a case study we refer to the AIFB portal - a place that is increasingly driven by Semantic Web technologies. We also discuss lessons learned from the ontology development of the AIFB portal..