This study examines the use of Bayesian Networks (BNs) for Stealth Assessment (SA) in digital game‐based learning (DGBL) environments. By integrating in‐game behavior tracking with embedded assessment scores, we investigate how interactive gameplay fosters learning gains. Data were collected from 632 middle school students participating in Mission HydroSci (MHS), a first-person 3D narrative adventure designed to teach water science and scientific argumentation. Using Static Bayesian Networks (SBNs), we modeled probabilistic dependencies among various in‐game behaviors, including evidence‐based argumentation, tool usage, dialogue engagement, and spatial exploration, and corresponding learning outcomes measured via pre‐ and post-assessments. Our analysis reveals distinct behavioral profiles strongly linked to positive learning gains. In particular, behavior patterns, including repeated engagement in argumentation tasks, strategic tool usage, and goal-oriented spatial exploration, emerge as key predictors of enhanced performance. Insights from the BN analysis inform the design of more effective DGBL environments and highlight the potential for real-time, adaptive assessment mechanisms that maintain gameplay immersion. Overall, this research offers a data-driven framework for understanding and optimizing learning trajectories in DGBL, providing practical guidelines for educators and game designers to enhance digital learning interventions.

Online social support communities can significantly improve health outcomes for individuals living with disease. Although they are well studied in the literature, little research examines how sociotechnical design changes influence the sustainability of support communities for different medical conditions. We compare the impact of a single design change on 49 disease‐specific health support forums hosted on the WebMD platform, a popular online health information service. A statistical analysis showcases changes in posting patterns before and after the design intervention; a subsequent interpretive examination of forum content reveals how the design change affected members' perceived affordances of the platform. Our findings suggest that, despite differences between communities, the design change triggered a common set of cascading effects: it made it difficult for core users to create and maintain relationships, that led them to ultimately leave the site, and, in turn, reduced the activity drawing newcomers to the platform. Using these findings, we argue that the design of sustainable and robust online communities must account for systemic, sociotechnical dynamics.

The rapid acceleration of corporate engagement with open source projects is drawing out new ways for CSCW researchers to consider the dynamics of these projects. Research must now consider the complex ecosystems within which open source projects are situated, including issues of for-profit motivations, brokering foundations, and corporate collaboration. Localized project considerations cannot reveal broader workings of an open source ecosystem, yet much empirical work is constrained to a local context. In response, we present eight observations from our eight-year engaged field study about the changing nature of open source projects. We ground these observations through 24 research questions that serve as primers to spark research ideas in this new reality of open source projects. This paper contributes to CSCW in social and crowd computing by delivering a rich and fresh look at corporately-engaged open source projects with a call for renewed focus and research into newly emergent areas of interest.

Mission HydroSci is a game-based 3D virtual environment for enacting transformational role-playing for middle school science students. Student-players will be engaged in a narrative about needing to investigate water resources and use scientific argumentation to complete missions critical to the survival and accomplishments of the members of their scientific enterprise. Our poster presents our progress in years 1 and 2 of a funded project to integrate pedagogical and gameplay objectives, and build mechanisms for purposeful player engagement and activity.

Social support can significantly improve health outcomes for individuals living with disease, and online forums have emerged as an important vehicle for social support. Whereas research has focused on the delivery and use of social support, little is known about how these communities are sustained. We describe one sociotechnical mechanism that enables sustainable communities to provide social support to a large number of people. We focus upon thirteen disease-specific discussion forums hosted by the WebMD online health community. In these forums, small, densely connected cores of members who maintain strong relationships generate the majority of support for others. Through content analysis we find they provide informational support to a large number of more itinerant members, but provide one another with community support. Based on these observations, we describe a sociotechnical mechanism of online support that is distinct from non-support oriented communities, and has implications for the design of self-sustaining online support systems.

Learning analytics (LA) has invested much effort in the investigation of students' behavior and performance within learning systems. This paper expands the influence of LA to students' behavior outside of learning systems and describes a novel machine learning model which automatically detects students' off-task behavior as students interact with a learning system, ASSISTments, based solely on log file data. We first operationalize social cognitive theory to introduce two new variables, affect states and problem set, both of which can be automatically derived from the logs, and can be considered to have a major influence on students' behavior. These two variables further work as the feature vector data for a K-means clustering algorithm in order to quantify students' different behavioral characteristics. This quantified variable representing student behavior type expands the feature space and contributes to the improvement of the various model performance compared with only time- and performance-related features. In addition, an advanced Hidden Naïve Bayes (HNB) algorithm is coded for off-task behavior detection and to show the best performance compared with traditional modeling techniques. Implications of the study are then discussed.

This full-day workshop focuses on building Big Social Data research competencies for scholars interested in issues of contribution quality and contributor performance in online co-production systems that generate value through contributions by volunteers. The workshop is designed to engage discussion and promote co-working through a hackathon format to stimulate productive conversation and learning, using shared data sets to provide a common focus for participants to engage questions of contribution quality and contributor performance with multiple disciplinary, theoretical, and analytical backgrounds.

In this paper we propose an automated strategy to assess participation in a multi-mode math discourse environment called Virtual Math Teams with Geogrebra (VMTwG). A holistic participation clustering algorithm is applied through the lens of activity theory. Our activity theory-informed algorithm is a step toward accelerating heuristic approaches to assessing collaborative work in synchronous technology mediated environments like VMTwG. Our Exploratory findings provide an example of a novel, time-efficient, valid, and reliable participatory learning assessment tool for teachers in computer mediated learning environments. Scaling online learning with a combination of computation and theory is the overall goal of the work this paper is situated within.

Humanitarian Free and Open Source Software (HFOSS) projects provide a real-world application with an approachable and welcoming community for both faculty and students. Many faculty members are excited by the prospect of their students contributing to HFOSS. They perceive it as an opportunity to engage students, regardless of race or gender, in projects that have societal impact. However trying something new in the classroom though can be daunting, and many barriers to entry exist. Locating an appropriate project, trying to figure out how to incorporate a dynamic, real-world project into the curriculum and learning how to interact with the project's community each present their own set of challenges. This BOF provides a gathering place for faculty who are interested in student participation in FOSS or HFOSS. The discussion will include an overview of an NSF-funded project, OpenFE. The goal of OpenFE is to develop faculty expertise in working with HFOSS projects and to develop curriculum materials that support faculty members in bringing this approach into their classrooms. The members of the OpenFE team will discuss plans for this grant and welcome both novices and experienced contributors to join us and provide feedback.

We present a methodological approach, called Group Informatics, for understanding the social connections that are created between members of technologically mediated groups. Our methodological approach supports focused thinking about how online groups differ from each other, and diverge from their face‐to‐face counterparts. Group Informatics is grounded in 5 years of empirical studies of technologically mediated groups in online learning, software engineering, online political discourse, crisis informatics, and other domains. We describe theGroupInformatics model and the related, 2‐phase methodological approach in detail. Phase one of the methodological approach centers on a set of guiding research questions aimed at directing the application ofGroupInformatics to new corpora of integrated electronic trace data and qualitative research data. Phase 2 of the methodological approach is a systematic set of steps for transforming electronic trace data into weighted social networks.

We describe a method for determining coordination requirements in collaborative software development. Our method uses "live" data based on developer activity rather than relying on historical data such as source code commits which is prevalent in existing methods. We introduce proximity, a measure of the strength of the work dependencies that lead to coordination requirements among members of a software development organization. Our proximity measure relies on a tool which captures the interactions of a developer with her IDE. It quantifies the similarity between records of interactions of developers as they work on their assigned tasks. We describe an algorithm that measures proximity between pairs of tasks or pairs of developers. Through an empirical study on an open source project that routinely records environment interaction data, we show how proximity accurately determines coordination requirements. The proximity measure thus enables proactive detection of coordination requirements and makes possible real time intervention and coordination facilitation via management-, design- and team-related decisions.

The US Navy directed its vast resources at the relief effort following the Haiti Earthquake on January 12, 2010. To coordinate with non-governmental-organizations (NGOs) participating in the relief effort, the US Navy used an online discussion forum. What follows is an examination of the emergence, rise, on-the-ground utility and decline of this "walled-garden" style discussion forum. Our findings show that most site activity is broadcast oriented and does not result in discussion, but in the small percentage of cases where discussion emerges, participants are focused on the exchange of medical, Global Information Systems (GIS) and equipment on the ground oriented information. We show how activity on the discussion forum changes over time, and corresponds with events on the ground in Haiti. Four archetypical users are profiled to demonstrate how invisible brokerage style leadership, identified through grounded theory analysis of posts, can be made visible through network analysis of interaction traces. Our findings have implications for the use of forum style, "walled garden" technology for coordination and information sharing in future crises.

Social computational systems emerge in the wild on popular social networking sites like Facebook and Twitter, but there remains confusion about the relationship between social interactions and the technical traces of interaction left behind through use. Twitter interactions and social experience are particularly challenging to make sense of because of the wide range of tools used to access Twitter (text message, website, iPhone, TweetDeck and others), and the emergent set of practices for annotating message context (hashtags, reply to's and direct messaging). Further, Twitter is used as a back channel of communication in a wide range of contexts, ranging from disaster relief to watching television. Our study examines Twitter as a transport protocol that is used differently in different socio-technical contexts, and presents an analysis of how researchers might begin to approach studies of Twitter interactions with a more reflexive stance toward the application programming interfaces (APIs) Twitter provides. We conduct a careful review of existing literature examining socio-technical phenomena on Twitter, revealing a collective inconsistency in the description of data gathering and analysis methods. In this paper, we present a candidate architecture and methodological approach for examining specific parts of the Twittersphere. Our contribution begins a discussion among social media researchers on the topic of how to systematically and consistently make sense of the social phenomena that emerge through Twitter. This work supports the comparative analysis of Twitter studies and the development of social media theories.

We propose an interdisciplinary workshop to explore key design principles of collaborative learning in the workplace. The workshop's theme is, simply "CSCL at the workplace". Our first workshop at ACM Group 2010, and the resulting book, raise an important set of issues and potentials for research, but does not solve the thorny and controversial issues. This workshop will be focused on for making progress on the identified issues. The ACM Group conference remains an ideal venue for a workshop on this topic because the North American and European communities who participate in Group include leading members of the international CSCL and CSCW communities. The proposed workshop will be a full day. It will open with a situating presentation by the organizers and, participant questions and proposed solutions aimed at the issues we have raised and begun to recognize, and focus working groups on the resolution of those issues in work to follow the conference. To participate in the workshop, discussants will be asked for a position paper of up to 2 pages in standard ACM format. Our edited book will be made available to participants in advance, and selected authors who will be present will provide overviews of their work and perspective in an interleaved way with the more action oriented working sessions.

We present a preliminary analysis of #widebate, a hashtag to identify discourse related to two debates in the June 2012, Wisconsin Gubernatorial recall election. Our analysis identifies the differences in discourse between the two debates. We find that only 14% of individuals participate in discourse surrounding both of the debates. Further, we identify differences in the way that the most active individuals in the discourse utilize syntactical features. Our findings contribute to the limited literature examining technologically-mediated discourse related to political debates.

A 16-student, completely online software design course was studied using social network analysis and grounded theory techniques. Bi-directional (read and post) log data of user activity was recorded to understand how small group networks change over time with activity type (individual, peer-to-peer, and small group). Network structure was revealed through sociograms and triangulated with discussion board topics and interview data on group experience. Results show significant differences in network structure across activity types, which are supported by open coding and axial coding of the text of member discussions and editing patterns of member work products. It is also indicated that bi-directional log data, contextualized to specific activities and artifacts, revealed a more accurate and complete description of small group activity than ordinary, uni-directional log data would have. Our findings have implications for tool development revealing group structure and software design for completely online group work.

We propose an interdisciplinary workshop to explore collaborative learning in the workplace. The workshop's theme is, simply at work. The ACM Group conference is an ideal venue for a workshop on this topic because the North American and European communities who participate in Group include leading members of the international CSCL and CSCW communities. The proposed workshop will be a full day. It will open with a situating presentation by the organizers and be followed by topically oriented small group breakout sessions. To participate in the workshop, discussants will be asked for a position paper of up to 4 pages in standard ACM format. Up to three papers will be selected for featured talks in the afternoon. The workshop will conclude with a decision on next steps. We have an outstanding book proposal with Springer on this topic, and an edited book is one possible next step.

We present a detailed descriptive analysis of the adoption and adaptation of common online tools by a newly forming small group with a cooperative work task. We compare their use of different tools over the course of successive specific cooperative activities, and describe how they use these tools as objects in the formation of a small online community. General patterns of participation that recognize the physical contexts of online group members, and specific patterns of interaction that influence the formation of an online community are explicated. The results of this study have implications for understanding how tools and tasks influence group formation and sense of community in online systems.