Git is widely used for collaborative software development, but it can be challenging for newcomers. While most learning tools focus on individual workflows, Git is inherently collaborative. We present GitAcademy, a browser-based learning platform that embeds a full Git environment with a split-view collaborative mode: learners work on their own local repositories connected to a shared remote repository, while simultaneously seeing their partner’s actions mirrored in real time. This design is not intended for everyday software development, but rather as a training simulator to build awareness of distributed states, coordination, and collaborative troubleshooting. In a within-subjects study with 13 pairs of learners, we found that the split-view interface enhanced social presence, supported peer teaching, and was consistently preferred over a single-view baseline, even though performance gains were mixed. We further discuss how split-view awareness can serve as a training-only scaffold for collaborative learning of Git and other distributed technical systems.

Juniors enter as AI‑natives, seniors adapted mid‑career. AI is not just changing how engineers code—it is reshaping who holds agency across work and professional growth. We contribute junior–senior accounts on their usage of agentic AI through a three-phase mixed-methods study: ACTA combined with a Delphi process with 5 seniors, an AI-assisted debugging task with 10 juniors, and blind reviews of junior prompt histories by 5 more seniors. We found that agency in software engineering is primarily constrained by organizational policies rather than individual preferences, with experienced developers maintaining control through detailed delegation while novices struggle between over-reliance and cautious avoidance. Seniors leverage pre-AI foundational instincts to steer modern tools and possess valuable perspectives for mentoring juniors in their early AI-encouraged career development. From synthesis of results, we suggest three practices that focus on preserving agency in software engineering for coding, learning, and mentorship, especially as AI grows increasingly autonomous.

Instructors are increasingly experimenting with AI chatbots for classroom support. To investigate how instructors adapt chatbots to their own contexts, we first analyzed existing resources that provide prompts for educational purposes. We identified ten common categories of customization, such as persona, guardrails, and personalization. We then conducted interviews with ten university STEM instructors and asked them to card-sort the categories into priorities. We found that instructors consistently prioritized the ability to customize chatbot behavior to align with course materials and pedagogical strategies and de-prioritized customizing persona/tone. However, their prioritization of other categories varied significantly by course size, discipline, and teaching style, even across courses taught by the same individual, highlighting that no single design can meet all contexts. These findings suggest that modular AI chatbots may provide a promising path forward. We offer design implications for educational developers building the next generation of customizable classroom AI systems.

Recent advances in generative AI have introduced a new programming paradigm—vibe coding, a natural language–driven mode of AI collaboration. While promising for adults, little is known about how children engage with this approach, especially in block-based environments. To explore this gap, we conducted workshops with children of varying Scratch experience (n=41) and interviewed five Scratch teachers. Our study investigates how vibe coding impacts children’s programming learning and practice, and what challenges arise. Findings show that vibe coding has both positive and negative impacts across three key contexts of children’s programming experience: acquisition, application, and creation. Across the stages of vibe coding—goal articulation, information interpretation, and outcome evaluation—children encounter distinct challenges. By examining the mismatches between core assumptions of vibe coding and children’s needs, and analyzing its applicability across different contexts, we offer child-centered design implications for future vibe coding systems and GenAI tools.

Syntax remains a major barrier for novices. Although block-based systems reduce or eliminate syntax errors, conditionals still challenge learners, likely because their semantics remain implicit. In this paper, we address this problem by introducing a semantics-first, state-visible programming approach inspired by the classic visual language Stagecast Creator. To demonstrate its usefulness, we designed Elephant, a unified, Karel-like research platform that supports three equally expressive programming paradigms: (i) semantics-first programming, (ii) block-based programming with the Blockly library, and (iii) text-based programming in JavaScript with domain-specific libraries. We then deployed Elephant in two within-subjects studies with secondary-school students (N = 39) to compare semantics-first programming to textual and block-based baselines, keeping the program semantics constant across modes and reducing cross-tool confounds. Results indicate, among other things, that semantics-first programming yields significantly higher task performance, suggesting that increasing the visibility of the program state during program composition could support greater outcomes in secondary computing education.

Intelligent systems have traditionally been designed as tools rather than collaborators, often lacking critical characteristics that collaboration partnerships require. Recent advances in large language model (LLM) agents open new opportunities for human-LLM-agent collaboration by enabling natural communication and various social and cognitive behaviors. Yet it remains unclear whether principles of computer-mediated collaboration established in HCI and CSCW persist, change, or fail when humans collaborate with LLM agents. To support systematic investigations of these questions, we introduce an open and configurable research platform for HCI researchers1. The platform’s modular design allows seamless adaptation of classic CSCW experiments and manipulation of theory-grounded interaction controls. We demonstrate the platform’s research efficacy and usability through three case studies: (1) two Shape FactoryHidden Profile experiment for information pooling with 16 participants, and (3) a participatory cognitive walkthrough with five HCI researchers to refine workflows of researcher interface for experiment setup and analysis.

Does AI understand human values? While this remains an open philosophical question, we take a pragmatic stance by introducing VAPT, the Value-Alignment Perception Toolkit, for studying how LLMs reflect people’s values and how people judge those reflections. 20 participants texted a chatbot over a month, then completed a 2-hour interview with our toolkit evaluating AI’s ability to extract (pull details regarding), embody (make decisions guided by), and explain (provide proof of) their values. 13 participants ultimately left our study convinced that AI can understand human values. Thus, we warn about “weaponized empathy”: a design pattern that may arise in interactions with value-aware, yet welfare-misaligned conversational agents. VAPT offers a new way to evaluate value-alignment in AI systems. We also offer design implications to evaluate and responsibly build AI systems with transparency and safeguards as AI capabilities grow more inscrutable, ubiquitous, and posthuman into the future.

As AI chatbots shift from tools to companions, critical questions arise: who controls the conversation in human–AI chatrooms? This paper explores perceived human and AI agency in sustained conversation. We report a month-long longitudinal study with 22 adults who chatted with “Day”, an LLM companion we built, followed by a semi-structured interview with post-hoc elicitation of notable moments, cross-participant chat reviews, and a ‘strategy reveal’ disclosing “Day’s” goal for each conversation. We discover agency manifests as an emergent, shared experience: as participants set boundaries and the AI steered intentions, control was co-constructed turn-by-turn. We introduce a 3-by-4 framework mapping actors (Human, AI, Hybrid) by their action (Intention, Execution, Adaptation, Delimitation), modulated by individual and environmental factors. We argue for translucent design (transparency-on-demand) and provide implications for agency self-aware conversational agents.

Designing user interfaces (UIs) is a critical step when launching products, building portfolios, or personalizing projects, yet end users without design expertise often struggle to articulate their intent and to trust design choices. Existing example-based tools either promote broad exploration, which can cause overwhelm and design drift, or require adapting a single example, risking design fixation. We present UI Remix, an interactive system that supports mobile UI design through an example-driven design workflow. Powered by a multimodal retrieval-augmented generation (MMRAG) model, UI Remix enables iterative search, selection, and adaptation of examples at both the global (whole interface) and local (component) level. To foster trust, it presents source transparency cues such as ratings, download counts, and developer information. In an empirical study with 24 end users, UI Remix significantly improved participants’ ability to achieve their design goals, facilitated effective iteration, and encouraged exploration of alternative designs. Participants also reported that source transparency cues enhanced their confidence in adapting examples. Our findings suggest new directions for AI-assisted, example-driven systems that empower end users to design with greater control, trust, and openness to exploration.

Artificial intelligence (AI) enables users to generate data visualizations from natural language descriptions, lowering the barrier to data exploration. However, AI-generated visualizations often present only the final output, lacking transparency and limiting users’ ability to verify, interpret, or refine the results. To address this, we introduce StepMIND, a generalizable visual framework that enhances explainability and interactivity in AI-generated data analysis pipelines. StepMIND integrates four dimensions: (1) Stepwise Refinement, allowing users to engage in the AI decision process; (2) Multimodal Explanations, combining natural language, structured notation, direct manipulation, and content visualization for accessible interpretation; (3) Bidirectional Editing, enabling seamless updates across modalities; and (4) Familiar Interaction Models, such as code editor and spreadsheet-based manipulations, to support both technical and non-technical users. To demonstrate its utility, we apply StepMIND in STAGE, a case study system for AI-assisted data visualization. A within-subject user study (N=20) shows that STAGE significantly improves user confidence and trust, reduces cognitive load, and facilitates both exploratory and corrective refinements. Our findings further suggest that StepMIND can generalize to broader AI-assisted workflows, offering a visible and interactive approach to explainable AI.

Generative AI has the potential to help teachers rapidly create classroom-ready visual materials, particularly in mathematics where diagrams and visual representations must be pedagogically meaningful and instructionally correct. However, current generative tools primarily support prompting and post-hoc editing, leaving open a key question for correctness-sensitive educational authoring: when in the generation pipeline should teachers exert control? In this paper, we investigate how the timing of human control in AI-Assisted generation shapes teachers' visual authoring practices in correctness-sensitive tasks. We introduce a design space of three stages of control: pre-generation control, where users specify intent solely through natural language prompts before generation; mid-generation control, where users inspect and confirm an explicit layout structure before the system completes generation; and post-generation control, where users directly modify AI-generated visuals after generation through object-level edits. In a within-subject, mixed-methods study with 24 primary mathematics teachers, post-generation control received higher ratings on predictability and correctness, while other subjective measures showed no reliable differences. Qualitative findings explain these differences by revealing workflow trade-offs: highly automated, pre-generation control supports rapid ideation but reduces perceived agency and predictability; mid-generation control improves structural alignment at the cost of additional effort; and post-generation control preserves user agency through low-cost, direct verification and correction. Together, these results suggest that in correctness-sensitive educational tasks, effective generative tools should align system behavior with teacher intent and support stage-dependent workflows that combine automation with direct manipulation.

Boolean algebra is foundational to programming, yet the terse textual syntax of boolean expressions does not map clearly onto the way that students reason about logical conditions. To help bridge this gap, we introduce Boolean Canvas, a direct-manipulation interface that lets learners construct visual boolean diagrams while the corresponding Python code is generated in real time. We report on a within-subjects study with 29 tertiary-level students who solved boolean-logic tasks in Python with and without Boolean Canvas. Task success, cognitive load, system enjoyment, and perceived usability were recorded. Results show that Boolean Canvas performs similarly to a traditional code editor across objective and self-reported measures. We reflect on the design and study outcomes, identifying which features supported learning, which did not, and why, and offer evidence-based recommendations for instructors and tool builders.

LLM-based chatbots like ChatGPT have become popular tools for assisting with coding tasks. However, they often produce isolated responses and lack mechanisms for social learning or contextual grounding. In contrast, online coding communities like Kaggle offer socially mediated learning environments that foster critical thinking, engagement, and a sense of belonging. Yet, growing reliance on LLMs risks diminishing participation in these communities and weakening their collaborative value. To address this, we propose Community-Enriched AI, a design paradigm that embeds social learning dynamics into LLM-based chatbots by surfacing user-generated content and social design features from online coding communities. Using this paradigm, we implemented a RAG-based AI chatbot leveraging resources from Kaggle to validate our design. Across two empirical studies involving 28 and 12 data science learners, respectively, we found that Community-Enriched AI significantly enhances user trust, encourages engagement with community, and effectively supports learners in solving data science tasks. We conclude by discussing design implications for AI assistance systems that bridge—rather than replace—online coding communities.

Large Language Model (LLM)-based in-application assistants, or copilots, can automate software tasks, but users often prefer learning by doing, raising questions about the optimal level of automation for an effective user experience. We investigated two automation paradigms by designing and implementing a fully automated copilot (AutoCopilot) and a semi-automated copilot (GuidedCopilot) that automates trivial steps while offering step-by-step visual guidance. In a user study (N=20) across data analysis and visual design tasks, GuidedCopilot outperformed AutoCopilot in user control, software utility, and learnability, especially for exploratory and creative tasks, while AutoCopilot saved time for simpler visual tasks. A follow-up design exploration (N=10) enhanced GuidedCopilot with task-and state-aware features, including in-context preview clips and adaptive instructions. Our findings highlight the critical role of user control and tailored guidance in designing the next generation of copilots that enhance productivity, support diverse skill levels, and foster deeper software engagement.

Decomposition is a fundamental skill in algorithmic programming, requiring learners to break down complex problems into smaller, manageable parts. However, current self-study methods, such as browsing reference solutions or using LLM assistants, often provide excessive or generic assistance that misaligns with learners' decomposition strategies, hindering independent problem-solving and critical thinking. To address this, we introduce Decomposition Box (DBox), an interactive LLM-based system that scaffolds and adapts to learners' personalized construction of a step tree through a "learner-LLM co-decomposition"approach, providing tailored support at an appropriate level. A within-subjects study (N=24) found that compared to the baseline, DBox significantly improved learning gains, cognitive engagement, and critical thinking. Learners also reported a stronger sense of achievement and found the assistance appropriate and helpful for learning. Additionally, we examined DBox's impact on cognitive load, identified usage patterns, and analyzed learners' strategies for managing system errors. We conclude with design implications for future AI-powered tools to better support algorithmic programming education.

The interdisciplinary field of Human-Computer Interaction (HCI) thrives on productive engagement with different domains, yet this engagement often breaks due to idiosyncratic writing styles and unfamiliar concepts. Inspired by the dialogic model of abstract metaphors, as well as the potential of Large Language Models (LLMs) to produce on-demand support, we investigate the use of metaphors to facilitate engagement between Science and Technology Studies (STS) and System HCI. Our reflective-style survey with early-career HCI researchers (N=48) reported that limited prior exposure to STS research can hinder perceived openness of the work, and ultimately interest in reading. The survey also revealed that metaphors enhance likelihood to continue reading STS papers, and alternative perspectives can build critical thinking skills to mitigate potential risks of LLM-generated metaphors. We lastly offer a specified model of metaphor exchange (within this generative context) that incorporates alternative perspectives to construct shared understanding in interdisciplinary engagement.

In the field of robotics, the process of locomotion control policy training is inherently iterative and exploratory. Practitioners often switch between multiple simulation and data analysis tools to observe robot postures and behaviors, track part movements, and compare reward data, which is a tedious process. To better understand their hurdles and requirements, we interviewed five robotics experts and analyzed representative figures from recent robotics publications to identify prevailing challenges and strategies for comparing and communicating locomotion policies. The main challenges include the lack of integrated simulation and visualization, difficulty in comparing multiple policies simultaneously, and the time-intensive process of creating polished visual presentations. Based on the insights, we introduce MRISA (Multi-Robot Interactive Simulation and Analysis Platform), an interactive tool designed to support exploratory analysis on pre-trained locomotion policies. MRISA integrates features including direct observation of one or multiple robots’ behaviors in a simulator, trajectories visualization with customized anchors, key measurement inspection in a timeline view, and key frames capturing. A user evaluation with 14 domain practitioners demonstrated that MRISA provides immediate insights, enabling practitioners to intuitively explore multiple dimensions of locomotion policies.

Peer Reviewed

Effective feedback is often timely and consistent but, with large cohorts, this is not always achievable. This study explored the potential of GPT4 to generate feedback on code readability for students enrolled in a CS1 Java course. We developed rubrics based on three readability criteria: naming, commenting, and formatting. We defined feedback criteria and incorporated them into GPT4 prompts to guide feedback generation. Results were mixed: while some feedback messages closely aligned with the rubrics, offering valuable insights, others fell short in providing corrective guidance. This highlights the potential and limitations of using LLMs to generate feedback on code readability. Future research could refine these methods to improve feedback consistency and quality.

Live coding is a powerful teaching technique in programming education that helps students connect theory to practice by observing the coding process in real-time. However, instructors face significant cognitive load challenges when simultaneously coding, explaining, debugging, and managing classroom interactions. This paper introduces Coducate, a code editor extension specifically designed to streamline instructor-led live coding sessions. Coducate aims to reduce the cognitive load of instructors by automating routine tasks while increasing student participation through collaborative coding features.

Live coding is a powerful teaching technique in programming education that helps students connect theory to practice by observing the coding process in real-time. However, instructors face significant cognitive load challenges when simultaneously coding, explaining, debugging, and managing classroom interactions. This paper introduces Coducate, a code editor extension specifically designed to streamline instructor-led live coding sessions. Coducate reduces instructor cognitive load by automating routine tasks while increasing student participation through collaborative coding features. Our showpiece includes an interactive demonstration of Coducate running on tablet devices, accompanied by a poster.

Developers often insert temporary “print” or “log” instructions into their code to help them better understand runtime behavior, usually when the code is not behaving as they expected. Despite the fact that such monitoring instructions, or “ad-hoc logs,” are so commonly used by developers, there is almost no existing literature that studies developers’ practices in how they use them. This paucity of knowledge of the use of these ephemeral logs may be largely due to the fact that they typically only exist in the developers’ local environments and are removed before they commit their code to their revision control system. In this work, we overcame this challenge by observing that developers occasionally mistakenly forget to remove such instructions before committing, and then they remove them shortly later. Additionally, we further studied such developer logging practices by watching and analyzing live-streamed coding videos. Through these empirical approaches, we presented where, how, and why developers use ad-hoc logs to better understand their code and its execution. We collected 27 GB of accidental commits that removed 548,880 ad-hoc logs in JavaScript from GitHub Archive repositories to provide the first large-scale dataset and empirical studies on ad-hoc logging practices. Our results revealed several illuminating findings, including a particular propensity for developers to use ad-hoc logs in asynchronous and callback functions. Our findings provided both empirical evidence and a valuable dataset for researchers and tool developers seeking to enhance ad-hoc logging practices, and potentially deepen our understanding of developers’ practices towards understanding of software’s runtime behaviors.

Monitoring in-class programming exercises can help instructors identify struggling students and common challenges. However, understanding students’ progress can be prohibitively difficult, particularly for multi-faceted problems that include multiple steps with complex interdependencies, have no predictable completion order, or involve evaluation criteria that are difficult to summarize across many students (e.g., exercises building interactive web-based user interfaces). We introduce Spark, a coding exercise monitoring dashboard designed to address these challenges. Spark allows instructors to flexibly group substeps into checkpoints based on exercise requirements, suggests automated tests for these checkpoints, and generates visualizations to track progress across steps. Spark also allows instructors to inspect intermediate outputs, providing deeper insights into solution variations. We also construct a dataset of 40 -minute keystroke coding data from $\mathrm{N}=22$ learners solving two web programming exercises and provide empirical insights into the perceived usefulness of Spark through a within-subjects evaluation with $\mathbf{1 6}$ programming instructors. Index Terms-programming education

Social media platforms increasingly employ proactive moderation techniques, such as detecting and curbing toxic and uncivil comments, to prevent the spread of harmful content. Despite these efforts, such approaches are often criticized for creating a climate of censorship and failing to address the underlying causes of uncivil behavior. Our work makes both theoretical and practical contributions by proposing and evaluating two types of emotion monitoring dashboards to enhance users' emotional awareness and mitigate hate speech. In a study involving 211 participants, we evaluate the effects of the two mechanisms on user commenting behavior and emotional experiences. The results reveal that these interventions effectively increase users' awareness of their emotional states and reduce hate speech. However, our findings also indicate potential unintended effects, including increased expression of negative emotions (Angry, Fear, and Sad) when discussing sensitive issues. These insights provide a basis for further research on integrating proactive emotion regulation tools into social media platforms to foster healthier digital interactions.

As AI technology continues to advance, the importance of human-AI collaboration becomes increasingly evident, with numerous studies exploring its potential in various fields. One vital field is data science, including feature engineering (FE), where both human ingenuity and AI capabilities play pivotal roles. Despite the existence of AI-generated recommendations for FE, there remains a limited understanding of how to effectively integrate and utilize humans’ and AI’s knowledge. To address this gap, we design a readily-usable prototype, human&AI-assisted FE in Jupyter notebooks. It harnesses the strengths of humans and AI to provide feature suggestions to users, seamlessly integrating these recommendations into practical workflows. Using the prototype as a research probe, we conducted an exploratory study to gain valuable insights into data science practitioners’ perceptions, usage patterns, and their potential needs when presented with feature suggestions from both humans and AI. Through qualitative analysis, we discovered that the “Creator” of the feature (i.e., AI or human) significantly influences users’ feature selection, and the semantic clarity of the suggested feature greatly impacts its adoption rate. Furthermore, our findings indicate that users perceive both differences and complementarity between features generated by humans and those generated by AI. Lastly, based on our study results, we derived a set of design recommendations for future human&AI FE design. Our findings show the collaborative potential between humans and AI in the field of FE.

Multi-stage programming tutorials are key learning resources for programmers, using progressive incremental steps to teach them how to build larger software systems. A good multi-stage tutorial describes the code clearly, explains the rationale and code changes for each step, and allows readers to experiment as they work through the tutorial. In practice, it is time-consuming for authors to create tutorials with these attributes. In this paper, we introduce Colaroid, an interactive authoring tool for creating high quality multi-stage tutorials. Colaroid tutorials are augmented computational notebooks, where snippets and outputs represent a snapshot of a project, with source code differences highlighted, complete source code context for each snippet, and the ability to load and tinker with any stage of the project in a linked IDE. In two laboratory studies, we found Colaroid makes it easy to create multi-stage tutorials, while offering advantages to readers compared to video and web-based tutorials.

Data science is characterized by evolution: since data science is exploratory, results evolve from moment to moment; since it can be collaborative, results evolve as the work changes hands. While existing tools help data scientists track changes in code, they provide less support for understanding the iterative changes that the code produces in the data. We explore the idea of visualizing differences in datasets as a core feature of exploratory data analysis, a concept we call Diff in the Loop (DITL). We evaluated DITL in a user study with 16 professional data scientists and found it helped them understand the implications of their actions when manipulating data. We summarize these findings and discuss how the approach can be generalized to different data science workflows.

Creating presentation slides is a critical but time-consuming task for data scientists. While researchers have proposed many AI techniques to lift data scientists’ burden on data preparation and model selection, few have targeted the presentation creation task. Based on the needs identified from a formative study, this paper presents NB2Slides, an AI system that facilitates users to compose presentations of their data science work. NB2Slides uses deep learning methods as well as example-based prompts to generate slides from computational notebooks, and take users’ input (e.g., audience background) to structure the slides. NB2Slides also provides an interactive visualization that links the slides with the notebook to help users further edit the slides. A follow-up user evaluation with 12 data scientists shows that participants believed NB2Slides can improve efficiency and reduces the complexity of creating slides. Yet, participants questioned the future of full automation and suggested a human-AI collaboration paradigm.

Data scientists benefit from collaboration: data scientists work across disciplines with a variety of stakeholders in practice [1] ; data scientists collaborate between the team to improve work efficiency [2] ; citizen data scientists collaborate in an open source manner to collectively explore topics of shared interests [3] , [4] .

Computational notebooks allow data scientists to express their ideas through a combination of code and documentation. However, data scientists often pay attention only to the code, and neglect creating or updating their documentation during quick iterations. Inspired by human documentation practices learned from 80 highly-voted Kaggle notebooks, we design and implement Themisto, an automated documentation generation system to explore how human-centered AI systems can support human data scientists in the machine learning code documentation scenario. Themisto facilitates the creation of documentation via three approaches: a deep-learning-based approach to generate documentation for source code, a query-based approach to retrieve online API documentation for source code, and a user prompt approach to nudge users to write documentation. We evaluated Themisto in a within-subjects experiment with 24 data science practitioners, and found that automated documentation generation techniques reduced the time for writing documentation, reminded participants to document code they would have ignored, and improved participants’ satisfaction with their computational notebook.

Computational notebooks allow data scientists to express their ideas through a combination of code and documentation. However, data scientists often pay attention only to the code and neglect the creation of the documentation in a notebook. In this work, we present a human-centered automation system, Themisto, that can support users to easily create documentation via three approaches: 1) We have developed and reported a GNN-augmented code documentation generation algorithm in a previous paper, which can generate documentation for a given source code; 2) Themisto also implements a query-based approach to retrieve the online API documentation as the summary for certain types of source code; 3) Lastly, Themistoalso enables a user prompt approach to motivate users to write documentation for some use cases that automation does not work well.

Data scientists face a steep learning curve in understanding a new domain for which they want to build machine learning (ML) models. While input from domain experts could offer valuable help, such input is often limited, expensive, and generally not in a form readily consumable by a model development pipeline. In this paper, we propose Ziva, a framework to guide domain experts in sharing essential domain knowledge to data scientists for building NLP models. With Ziva, experts are able to distill and share their domain knowledge using domain concept extractors and five types of label justification over a representative data sample. The design of Ziva is informed by preliminary interviews with data scientists, in order to understand current practices of domain knowledge acquisition process for ML development projects. To assess our design, we run a mix-method case-study to evaluate how Ziva can facilitate interaction between domain experts and data scientists. Our results highlight that (1) domain experts are able to use Ziva to provide rich domain knowledge, while maintaining low mental load and stress levels; and (2) data scientists find Ziva’s output helpful for learning essential information about the domain, offering scalability of information, and lowering the burden on domain experts to share knowledge. We conclude this work by experimenting with building NLP models using the Ziva output for our case study.

The development of AI applications is a multidisciplinary effort, involving multiple roles collaborating with the AI developers, an umbrella term we use to include data scientists and other AI-adjacent roles on the same team. During these collaborations, there is a knowledge mismatch between AI developers, who are skilled in data science, and external stakeholders who are typically not. This difference leads to communication gaps, and the onus falls on AI developers to explain data science concepts to their collaborators. In this paper, we report on a study including analyses of both interviews with AI developers and artifacts they produced for communication. Using the analytic lens of shared mental models, we report on the types of communication gaps that AI developers face, how AI developers communicate across disciplinary and organizational boundaries, and how they simultaneously manage issues regarding trust and expectations.

Peer assessment, as a form of collaborative learning, can engage students in active learning and improve their learning gains. However, current teaching platforms and programming environments provide little support to integrate peer assessment for in-class programming exercises. We identified challenges in conducting such exercises and adopting peer assessment through formative interviews with instructors of introductory programming courses. To address these challenges, we introduce PuzzleMe, a tool to help Computer Science instructors to conduct engaging in-class programming exercises. PuzzleMe leverages peer assessment to support a collaboration model where students provide timely feedback on their peers' work. We propose two assessment techniques tailored to in-class programming exercises: live peer testing and live peer code review. Live peer testing can improve students' code robustness by allowing them to create and share lightweight tests with peers. Live peer code review can improve code understanding by intelligently grouping students to maximize meaningful code reviews. A two-week deployment study revealed that PuzzleMe encourages students to write useful test cases, identify code problems, correct misunderstandings, and learn a diverse set of problem-solving approaches from peers.

When teams of data scientists collaborate on computational notebooks, their discussions often contain valuable insight into their design decisions. These discussions not only explain analysis in the current notebook but also alternative paths, which are often poorly documented. However, these discussions are disconnected from the notebooks for which they could provide valuable context. We propose Callisto, an extension to computational notebooks that captures and stores contextual links between discussion messages and notebook elements with minimal effort from users. Callisto allows notebook readers to better understand the current notebook content and the overall problem-solving process that led to it, by making it possible to browse the discussions and code history relevant to any part of the notebook. This is particularly helpful for onboarding new notebook collaborators to avoid misinterpretations and duplicated work, as we found in a two-stage evaluation with 32 data science students.

Programming support methods, like discussion fo-rums and office hours, are important in CS education, but difficult to scale. In this paper, we introduce EdCode, a system that allows students to seek remote instructional support within their IDE in a way that resembles in-person support. It also allows instructors to provide contextualized responses by referencing students' code, and curate and publish their answers for an entire class by selecting only the relevant part of the code referenced, thereby helping to avoid plagiarism. We evaluated EdCode with a series of usability studies and identified benefits and challenges for its use in programming courses. Students found that the perceived quality of support from EdCode was comparable to that of support from in-person office hours, and both students and instructors found publishing and viewing other students' answers helpful.

The need for learning about emerging technologies and technical concepts among the general population is increasing, but formal explanations from online encyclopedias, textbooks, and articles are often rich in technical jargon and can be challenging to grasp. In this paper, we explore a novel approach for explaining technical concepts to non-technical users through the design of JargonLite, an interactive dictionary that shows how technical concepts can be used in everyday conversations. We evaluated curated conversation-driven explanations with 12 users who had little or no technical training and wanted to learn about big data concepts. We found that users perceived conversation-driven explanations to be easy to understand and these explanations helped them to maintain focus. We discuss the potential of using conversation-driven explanations as a learning tool for non-technical users and reflect on the advantages and disadvantages of this approach.

Effective collaboration in data science can leverage domain expertise from each team member and thus improve the quality and efficiency of the work. Computational notebooks give data scientists a convenient interactive solution for sharing and keeping track of the data exploration process through a combination of code, narrative text, visualizations, and other rich media. In this paper, we report how synchronous editing in computational notebooks changes the way data scientists work together compared to working on individual notebooks. We first conducted a formative survey with 195 data scientists to understand their past experience with collaboration in the context of data science. Next, we carried out an observational study of 24 data scientists working in pairs remotely to solve a typical data science predictive modeling problem, working on either notebooks supported by synchronous groupware or individual notebooks in a collaborative setting. The study showed that working on the synchronous notebooks improves collaboration by creating a shared context, encouraging more exploration, and reducing communication costs. However, the current synchronous editing features may lead to unbalanced participation and activity interference without strategic coordination. The synchronous notebooks may also amplify the tension between quick exploration and clear explanations. Building on these findings, we propose several design implications aimed at better supporting collaborative editing in computational notebooks, and thus improving efficiency in teamwork among data scientists.

Conversational programmers represent a class of learners who are not required to write any code, yet try to learn programming to improve their participation in technical conversations. We carried out interviews with 23 conversational programmers to better understand the challenges they face in technical conversations, what resources they choose to learn programming, how they perceive the learning process, and to what extent learning programming actually helps them. Among our key findings, we found that conversational programmers often did not know where to even begin the learning process and ended up using formal and informal learning resources that focus largely on programming syntax and logic. However, since the end goal of conversational programmers was not to build artifacts, modern learning resources usually failed these learners in their pursuits of improving their technical conversations. Our findings point to design opportunities in HCI to invent learner-centered approaches that address the needs of conversational programmers and help them establish common ground in technical conversations.

Users can often find it difficult to sift through dense help pages, tutorials, Q&A sites, blogs, and wikis to locate useful task-specific instructions for feature-rich applications. We present Social CheatSheet, an interactive information overlay that can appear atop any existing web application and retrieve relevant step-by-step instructions and tutorials curated by other users. Based on results of our formative study, the system offers several features for users to search, browse, filter, and bookmark community-generated help content and to ask questions and clarifications. Furthermore, Social CheatSheet includes embedded curation features for users to generate their own annotated notes and tutorials that can be kept private or shared with the user community. A weeklong deployment study with 15 users showed that users found Social CheatSheet to be useful and they were able to easily both add their own curated content and locate content generated by other users. The majority of users wanted to keep using the system beyond the deployment. We discuss the potential of Social CheatSheet as an application-independent platform driven by community curation efforts to lower the barriers in finding relevant help and instructions.