arXiv subjects

Joseph Seering

Publications and source records attributed to Joseph Seering.

At least 19 recordsLinked to original sources

arXiv2026

Ethics Training Agents: Facilitating Group-Based Ethics Education with Role-Playing and Discussion for Ethical Reflection and Exploration

Group-based ethics training for Science, Technology, Engineering and Mathematics (STEM) students is a complex challenge, requiring substantial resources and expertise. While activity-based teaching methods, such as role-playing and discussions, are commonly employed to simulate real-world scenarios, current practices are often manual and lack integration with effective online platforms for supporting group-based ethical discussions. In this work, we propose Ethics Training Agents, a group discussion system that leverages multiple LLM participants embodying distinct ethical orientations, along with a moderator agent, to enable structured human-AI group ethical discussions for collaborative reflection. We conduct a user study with 45 undergraduate STEM students to evaluate the learning outcomes and user experience. The results show that our system supports engagement, coordination, and perspective-taking in group discussions and has a positive influence on ethical sensitivity. We also discuss practical design strategies for integrating multiple LLM agents into multi-human group settings to facilitate ethics training for STEM students.

cs.HC↗

arXiv2026

TIDES: A Longitudinal Bilingual Dataset for Modeling Multi-Party Social Dynamics

Group conversations are fundamental to human collaboration, yet standard large language models (LLMs) still struggle with the complexities of multi-party interaction. This challenge persists in part because existing group conversation datasets are often limited to short-term lab settings with contrived tasks, failing to capture the long-term social dynamics of real-world teams. To bridge this gap, we introduce TIDES, a high-resolution longitudinal dataset tracking 12 university project teams over a full semester. Comprising 75,971 utterances in both English and Korean from in-person meetings, TIDES provides a naturalistic record of teams working on self-managed projects. Our socio-structural annotations-covering interaction types, emergent roles, and development stages-allow for modeling of team evolution over months. Experiments show that fine-tuning on TIDES improves next-speaker prediction by 13.8 percentage points over a bigram baseline (64.53%) and yields performance comparable to strong proprietary zero-shot models. The model also comes within 2.1 percentage points of the published state of the art on the AMI Meeting Corpus while using approximately 42% less training data. However, human evaluations suggest that better next-speaker prediction does not necessarily yield more natural or coherent utterances, as fine-tuned models were generally less preferred than vanilla models. This potential mismatch motivates further study of how structural modeling can support natural multi-party generation.

cs.CL↗

arXiv2026

SLALOM: Simulation Lifecycle Analysis via Longitudinal Observation Metrics for Social Simulation

Large Language Model (LLM) agents offer a potentially-transformative path forward for generative social science but face a critical crisis of validity. Current simulation evaluation methodologies suffer from the "stopped clock" problem: they confirm that a simulation reached the correct final outcome while ignoring whether the trajectory leading to it was sociologically plausible. Because the internal reasoning of LLMs is opaque, verifying the "black box" of social mechanisms remains a persistent challenge. In this paper, we introduce SLALOM (Simulation Lifecycle Analysis via Longitudinal Observation Metrics), a framework that shifts validation from outcome verification to process fidelity. Drawing on Pattern-Oriented Modeling (POM), SLALOM treats social phenomena as multivariate time series that must traverse specific SLALOM gates, or intermediate waypoint constraints representing distinct phases. By utilizing Dynamic Time Warping (DTW) to align simulated trajectories with empirical ground truth, SLALOM offers a quantitative metric to assess structural realism, helping to differentiate plausible social dynamics from stochastic noise and contributing to more robust policy simulation standards.

cs.MA↗

arXiv2025

AssurAI: Experience with Constructing Korean Socio-cultural Datasets to Discover Potential Risks of Generative AI

The rapid evolution of generative AI necessitates robust safety evaluations. However, current safety datasets are predominantly English-centric, failing to capture specific risks in non-English, socio-cultural contexts such as Korean, and are often limited to the text modality. To address this gap, we introduce AssurAI, a new quality-controlled Korean multimodal dataset for evaluating the safety of generative AI. First, we define a taxonomy of 35 distinct AI risk factors, adapted from established frameworks by a multidisciplinary expert group to cover both universal harms and relevance to the Korean socio-cultural context. Second, leveraging this taxonomy, we construct and release AssurAI, a large-scale Korean multimodal dataset comprising 11,480 instances across text, image, video, and audio. Third, we apply the rigorous quality control process used to ensure data integrity, featuring a two-phase construction (i.e., expert-led seeding and crowdsourced scaling), triple independent annotation, and an iterative expert red-teaming loop. Our pilot study validates AssurAI's effectiveness in assessing the safety of recent LLMs. We release AssurAI to the public to facilitate the development of safer and more reliable generative AI systems for the Korean community.

cs.AI↗

arXiv2025

CrisisNews: A Dataset Mapping Two Decades of News Articles on Online Problematic Behavior at Scale

As social media adoption grows globally, online problematic behaviors increasingly escalate into large-scale crises, requiring an evolving set of mitigation strategies. While HCI research often analyzes problematic behaviors with pieces of user-generated content as the unit of analysis, less attention has been given to event-focused perspectives that track how discrete events evolve. In this paper, we examine 'social media crises': discrete patterns of problematic behaviors originating and evolving within social media that cause larger-scale harms. Using global news coverage, we present a dataset of 93,250 news articles covering social media-endemic crises from the past 20 years. We analyze a representative subset to classify stakeholder roles, behavior types, and outcomes, uncovering patterns that inform more nuanced classification of social media crises beyond content-based descriptions. By adopting a wider perspective, this research seeks to inform the design of safer platforms, enabling proactive measures to mitigate crises and foster more trustworthy online environments.

cs.SI↗

arXiv2025

How Far I'll Go: Imagining Futures of Conversational AI with People with Visual Impairments Through Design Fiction

People with visual impairments (PVI) use a variety of assistive technologies to navigate their daily lives, and conversational AI (CAI) tools are a growing part of this toolset. Much existing HCI research has focused on the technical capabilities of current CAI tools, but in this paper, we instead examine how PVI themselves envision potential futures for living with CAI. We conducted a study with 14 participants with visual impairments using an audio-based Design Fiction probe featuring speculative dialogues between participants and a future CAI. Participants imagined using CAI to expand their boundaries by exploring new opportunities or places, but also voiced concerns about balancing reliance on CAI with maintaining autonomy, the need to consider diverse levels of vision-loss, and enhancing visibility of PVI for greater inclusion. We discuss implications for designing CAI that support genuine agency for PVI based on the future lives they envisioned.

cs.HC↗

arXiv2025

Prototyping Digital Social Spaces through Metaphor-Driven Design: Translating Spatial Concepts into an Interactive Social Simulation

Social media platforms are central to communication, yet their designs remain narrowly focused on engagement and scale. While researchers have proposed alternative visions for online spaces, these ideas are difficult to prototype within platform constraints. In this paper, we introduce a metaphor-driven system to help users imagine and explore new social media environments. The system translates users' metaphors into structured sets of platform features and generates interactive simulations populated with LLM-driven agents. To evaluate this approach, we conducted a study where participants created and interacted with simulated social media spaces. Our findings show that metaphors allow users to express distinct social expectations, and that perceived authenticity of the simulation depended on how well it captured dynamics like intimacy, participation, and temporal engagement. We conclude by discussing how metaphor-driven simulation can be a powerful design tool for prototyping alternative social architectures and expanding the design space for future social platforms.

cs.HC↗

arXiv2025

Fostering Collective Discourse: A Distributed Role-Based Approach to Online News Commenting

Current news commenting systems are designed based on implicitly individualistic assumptions, where discussion is the result of a series of disconnected opinions. This often results in fragmented and polarized conversations that fail to represent the spectrum of public discourse. In this work, we develop a news commenting system where users take on distributed roles to collaboratively structure the comments to encourage a connected, balanced discussion space. Through a within-subject, mixed-methods evaluation (N=38), we find that the system supported three stages of participation: understanding issues, collaboratively structuring comments, and building a discussion. With our system, users' comments displayed more balanced perspectives and a more emotionally neutral argumentation. Simultaneously, we observed reduced argument strength compared to a traditional commenting system, indicating a trade-off between inclusivity and depth. We conclude with design considerations and trade-offs for introducing distributed roles in news commenting system design.

cs.HC↗

arXiv2025

Botender: Supporting Communities in Collaboratively Designing AI Agents through Case-Based Provocations

AI agents, or bots, serve important roles in online communities. However, they are often designed by outsiders or a few tech-savvy members, leading to bots that may not align with the broader community's needs. How might communities collectively shape the behavior of community bots? We present Botender, a system that enables communities to collaboratively design LLM-powered bots without coding. With Botender, community members can directly propose, iterate on, and deploy custom bot behaviors tailored to community needs. Botender facilitates testing and iteration on bot behavior through case-based provocations: interaction scenarios generated to spark user reflection and discussion around desirable bot behavior. A validation study found these provocations more useful than standard test cases for revealing improvement opportunities and surfacing disagreements. During a five-day deployment across six Discord servers, Botender supported communities in tailoring bot behavior to their specific needs, showcasing the usefulness of case-based provocations in facilitating collaborative bot design.

cs.HC↗

arXiv2025

Inject, Fork, Compare: Defining an Interaction Vocabulary for Multi-Agent Simulation Platforms

LLM-based multi-agent simulations are a rapidly growing field of research, but current simulations often lack clear modes for interaction and analysis, limiting the "what if" scenarios researchers are able to investigate. In this demo, we define three core operations for interacting with multi-agent simulations: inject, fork, and compare. Inject allows researchers to introduce external events at any point during simulation execution. Fork creates independent timeline branches from any timestamp, preserving complete state while allowing divergent exploration. Compare facilitates parallel observation of multiple branches, revealing how different interventions lead to distinct emergent behaviors. Together, these operations establish a vocabulary that transforms linear simulation workflows into interactive, explorable spaces. We demonstrate this vocabulary through a commodity market simulation with fourteen AI agents, where researchers can inject contrasting events and observe divergent outcomes across parallel timelines. By defining these fundamental operations, we provide a starting point for systematic causal investigation in LLM-based agent simulations, moving beyond passive observation toward active experimentation.

cs.MA↗

arXiv2025

Evalet: Evaluating Large Language Models through Functional Fragmentation

Practitioners increasingly rely on Large Language Models (LLMs) to evaluate generative AI outputs through "LLM-as-a-Judge" approaches. However, these methods produce holistic scores that obscure which specific elements influenced the assessments. We propose functional fragmentation, a method that dissects each output into key fragments and interprets the rhetoric functions that each fragment serves relative to evaluation criteria -- surfacing the elements of interest and revealing how they fulfill or hinder user goals. We instantiate this approach in Evalet, an interactive system that visualizes fragment-level functions across many outputs to support inspection, rating, and comparison of evaluations. A user study (N=10) found that, while practitioners struggled to validate holistic scores, our approach helped them identify 48% more evaluation misalignments. This helped them calibrate trust in LLM evaluations and rely on them to find more actionable issues in model outputs. Our work shifts LLM evaluation from quantitative scores toward qualitative, fine-grained analysis of model behavior.

cs.HC↗

arXiv2025

Mapping Community Appeals Systems: Lessons for Community-led Moderation in Multi-Level Governance

Platforms are increasingly adopting industrial models of moderation that prioritize scalability and consistency, frequently at the expense of context-sensitive and user-centered values. Building on the multi-level governance framework that examines the interdependent relationship between platforms and middle-level communities, we investigate community appeals systems on Discord as a model for successful community-led governance. We investigate how Discord servers operationalize appeal systems through a qualitative interview study with focus groups and individual interviews with 17 community moderators. Our findings reveal a structured appeals process that balances scalability, fairness, and accountability while upholding community-centered values of growth and rehabilitation. Communities design these processes to empower users, ensuring their voices are heard in moderation decisions and fostering a sense of belonging. This research provides insights into the practical implementation of community-led governance in a multi-level governance framework, illustrating how communities can maintain their core principles while integrating procedural fairness and tool-based design. We discuss how platforms can gain insights from community-led moderation work to motivate governance structures that effectively balance and align the interests of multiple stakeholders.

cs.HC↗

arXiv2025

HateBuffer: Safeguarding Content Moderators' Mental Well-Being through Hate Speech Content Modification

Hate speech remains a persistent and unresolved challenge in online platforms. Content moderators, working on the front lines to review user-generated content and shield viewers from hate speech, often find themselves unprotected from the mental burden as they continuously engage with offensive language. To safeguard moderators' mental well-being, we designed HateBuffer, which anonymizes targets of hate speech, paraphrases offensive expressions into less offensive forms, and shows the original expressions when moderators opt to see them. Our user study with 80 participants consisted of a simulated hate speech moderation task set on a fictional news platform, followed by semi-structured interviews. Although participants rated the hate severity of comments lower while using HateBuffer, contrary to our expectations, they did not experience improved emotion or reduced fatigue compared with the control group. In interviews, however, participants described HateBuffer as an effective buffer against emotional contagion and the normalization of biased opinions in hate speech. Notably, HateBuffer did not compromise moderation accuracy and even contributed to a slight increase in recall. We explore possible explanations for the discrepancy between the perceived benefits of HateBuffer and its measured impact on mental well-being. We also underscore the promise of text-based content modification techniques as tools for a healthier content moderation environment.

cs.HC↗

arXiv2025

The Design Space for Online Restorative Justice Tools: A Case Study with ApoloBot

Volunteer moderators use various strategies to address online harms within their communities. Although punitive measures like content removal or account bans are common, recent research has explored the potential for restorative justice as an alternative framework to address the distinct needs of victims, offenders, and community members. In this study, we take steps toward identifying a more concrete design space for restorative justice-oriented tools by developing ApoloBot, a Discord bot designed to facilitate apologies when harm occurs in online communities. We present results from two rounds of interviews: first, with moderators giving feedback about the design of ApoloBot, and second, after a subset of these moderators have deployed ApoloBot in their communities. This study builds on prior work to yield more detailed insights regarding the potential of adopting online restorative justice tools, including opportunities, challenges, and implications for future designs.

cs.HC↗

arXiv2025

Leveling Up Together: Fostering Positive Growth and Safe Online Spaces for Teen Roblox Developers

Creating games together is both a playful and effective way to develop skills in computational thinking, collaboration, and more. However, game development can be challenging for younger developers who lack formal training. While teenage developers frequently turn to online communities for peer support, their experiences may vary. To better understand the benefits and challenges teens face within online developer communities, we conducted interviews with 18 teenagers who created games or elements in Roblox and received peer support from one or more online Roblox developer communities. Our findings show that developer communities provide teens with valuable resources for technical, social, and career growth. However, teenagers also struggle with inter-user conflicts and a lack of community structure, leading to difficulties in handling complex issues that may arise, such as financial scams. Based on these insights, we propose takeaways for creating positive and safe online spaces for teenage game creators.

cs.HC↗

arXiv2025

Less Talk, More Trust: Understanding Players' In-game Assessment of Communication Processes in League of Legends

In-game team communication in online multiplayer games has shown the potential to foster efficient collaboration and positive social interactions. Yet players often associate communication within ad hoc teams with frustration and wariness. Though previous works have quantitatively analyzed communication patterns at scale, few have identified the motivations of how a player makes in-the-moment communication decisions. In this paper, we conducted an observation study with 22 League of Legends players by interviewing them during Solo Ranked games on their use of four in-game communication media (chat, pings, emotes, votes). We performed thematic analysis to understand players' in-context assessment and perception of communication attempts. We demonstrate that players evaluate communication opportunities on proximate game states bound by player expectations and norms. Our findings illustrate players' tendency to view communication, regardless of its content, as a precursor to team breakdowns. We build upon these findings to motivate effective player-oriented communication design in online games.

cs.HC↗

arXiv2025

"It's Great Because It's Ran By Us": Empowering Teen Volunteer Discord Moderators to Design Healthy and Engaging Youth-Led Online Communities

Online communities can offer many benefits for youth including peer learning, cultural expression, and skill development. However, most HCI research on youth-focused online communities has centered communities developed by adults for youth rather than by the youth themselves. In this work, we interviewed 11 teenagers (ages 13-17) who moderate online Discord communities created by youth, for youth. Participants were identified by Discord platform staff as leaders of well-moderated servers through an intensive exam and application-based process. We also interviewed 2 young adults who volunteered as mentors of some of our teen participants. We present our findings about the benefits, motivations, and risks of teen-led online communities, as well as the role of external stakeholders of these youth spaces. We contextualize our work within the broader teen online safety landscape to provide recommendations to better support, encourage, and protect teen moderators and their online communities. This empirical work contributes one of the first studies to date with teen Discord moderators and aims to empower safe youth-led online communities.

cs.HC↗

arXiv2023

Hate Raids on Twitch: Echoes of the Past, New Modalities, and Implications for Platform Governance

In the summer of 2021, users on the livestreaming platform Twitch were targeted by a wave of "hate raids," a form of attack that overwhelms a streamer's chatroom with hateful messages, often through the use of bots and automation. Using a mixed-methods approach, we combine a quantitative measurement of attacks across the platform with interviews of streamers and third-party bot developers. We present evidence that confirms that some hate raids were highly-targeted, hate-driven attacks, but we also observe another mode of hate raid similar to networked harassment and specific forms of subcultural trolling. We show that the streamers who self-identify as LGBTQ+ and/or Black were disproportionately targeted and that hate raid messages were most commonly rooted in anti-Black racism and antisemitism. We also document how these attacks elicited rapid community responses in both bolstering reactive moderation and developing proactive mitigations for future attacks. We conclude by discussing how platforms can better prepare for attacks and protect at-risk communities while considering the division of labor between community moderators, tool-builders, and platforms.

cs.CY↗