Mirror to Companion: Exploring Roles, Values, and Risks of AI Self-Clones through Story Completion
説明

Advancing technologies enable machine learning applications that replicate the appearance, behavior, and thought patterns of users based on their personal data. Termed as AI self-clones, these digital doppelgangers present introspective opportunities and existential risks, as they might amplify self-awareness or echo problematic self-views. In our participatory design fiction study, we involved 20 diverse individuals to explore the values and risks they associate with creating AI self-clones. Our participants conceptualized AI self-clones by the roles these clones could assume, such as mirror, probe, companion, delegate, and representative. The perceived values and risks tend to correspond to these roles. For example, using self-clones as representatives could enhance relationship maintenance, yet it might also lead to diminished authenticity in personal connections; utilizing self-clones as probes to explore life scenarios could aid decision-making, but it might amplify regrets about unchosen paths. This research lays the groundwork for an ethical design of AI self-clone applications.

日本語まとめ
読み込み中…
読み込み中…
From Solo to Social: Exploring the Dynamics of Player Cooperation in a Co-located Cooperative Exergame
説明

Digital games offer rich social experiences and promote valuable skills, but they fall short in addressing physical inactivity. Exergames, which combine exercise with gameplay, have the potential to tackle this issue. However, current exergames are primarily single-player or competitive. To explore the social benefits of cooperative exergaming, we designed a custom co-located cooperative exergame that features three distinct forms of cooperation: Free (baseline), Coupled, and Concurrent. We conducted a within-participants, mixed-methods study (N=24) to evaluate these designs and their impact on players' enjoyment, motivation, and performance. Our findings reveal that cooperative play improves social experiences. It drives increased team identification and relatedness. Furthermore, our qualitative findings support cooperative exergame play. This has design implications for creating exergames that effectively address players' exercise and social needs. Our research contributes guidance for developers and researchers who want to create more socially enriching exergame experiences.

日本語まとめ
読み込み中…
読み込み中…
Plan-Then-Execute: An Empirical Study of User Trust and Team Performance When Using LLM Agents As A Daily Assistant
説明

Since the explosion in popularity of ChatGPT, large language models (LLMs) have continued to impact our everyday lives. Equipped with external tools that are designed for a specific purpose (e.g., for flight booking or an alarm clock), LLM agents exercise an increasing capability to assist humans in their daily work. Although LLM agents have shown a promising blueprint as daily assistants, there is a limited understanding of how they can provide daily assistance based on planning and sequential decision making capabilities. We draw inspiration from recent work that has highlighted the value of `\textit{LLM-modulo}' setups in conjunction with humans-in-the-loop for planning tasks. We conducted an empirical study ($N$ = 248) of LLM agents as daily assistants in six commonly occurring tasks with different levels of risk typically associated with them (e.g., flight ticket booking and credit card payments). To ensure user agency and control over the LLM agent, we adopted LLM agents in a plan-then-execute manner, wherein the agents conducted step-wise planning and step-by-step execution in a simulation environment. We analyzed how user involvement at each stage affects their trust and collaborative team performance. Our findings demonstrate that LLM agents can be a double-edged sword --- (1) they can work well when a high-quality plan and necessary user involvement in execution are available, and (2) users can easily mistrust the LLM agents with plans that seem plausible. We synthesized key insights for using LLM agents as daily assistants to calibrate user trust and achieve better overall task outcomes. Our work has important implications for the future design of daily assistants and human-AI collaboration with LLM agents.

日本語まとめ
読み込み中…
読み込み中…
Queue Player: Investigating Distributed Co-Listening Experiences for Social Connection across Space, Time, and Tempo
説明

We describe the design and deployment of Queue Player, four networked domestic music players that combine music listening histories of close friends to explore new potentialities for interacting with this shared archive. We deployed the Queue Players with four close friends living in separate homes for six weeks. Our goals are to (i) explore how this system might enable co-listening experiences that foster social presence, interaction, and reflection and (ii) empirically explore conceptual propositions related to slow technology. Findings revealed that, after overcoming initial frictions, Queue Player became integrated in participants’ lives and triggered a range of social interactions and reflections on past life experiences. They also showed that Queue Player provoked questions on the benefits and limits of data capturing one’s life history as well as the role and pace of technology in everyday life at home. Findings are interpreted to present opportunities for future HCI research and practice.

日本語まとめ
読み込み中…
読み込み中…
ClueCart: Supporting Game Story Interpretation and Narrative Inference from Fragmented Clues
説明

Indexical storytelling is gaining popularity in video games, where the narrative unfolds through fragmented clues. This approach fosters player-generated content and discussion, as story interpreters piece together the overarching narrative from these scattered elements. However, the fragmented and non-linear nature of the clues makes systematic categorization and interpretation challenging, potentially hindering efficient story reconstruction and creative engagement. To address these challenges, we first proposed a hierarchical taxonomy to categorize narrative clues, informed by a formative study. Using this taxonomy, we designed ClueCart, a creativity support tool aimed at enhancing creators' ability to organize story clues and facilitate intricate story interpretation. We evaluated ClueCart through a between-subjects study (N=40), using Miro as a baseline. The results showed that ClueCart significantly improved creators' efficiency in organizing and retrieving clues, thereby better supporting their creative processes. Additionally, we offer design insights for future studies focused on player-centric narrative analysis.

日本語まとめ
読み込み中…
読み込み中…
Less Talk, More Trust: Understanding Players' In-game Assessment of Communication Processes in League of Legends
説明

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.

日本語まとめ
読み込み中…
読み込み中…
Cinema Multiverse Lounge: Enhancing Film Appreciation via Multi-Agent Conversations
説明

Advancements in large language models (LLMs) enable the development of interactive systems that enhance user engagement with cinematic content. We introduce \textit{Cinema Multiverse Lounge}, a multi-agent conversational system where users interact with LLM-based agents embodying diverse film-related personas. We investigate how user interactions with these agents influence their film appreciation. Thirty participants engaged in three discussion sessions, freely selecting persona agents such as film characters, filmmakers, or anonymous audiences. We explored how users composed different combinations of personas, the factors affecting their engagement and interpretation, and how diverse perspectives influenced film appreciation. Results indicate that interactions with varied agents enhanced participants’ appreciation by enabling the exploration of multiple viewpoints and fostering deeper narrative engagement. Moreover, the unexpected clashes between different worldviews added a fresh and enjoyable layer to the interactions. Our findings provide empirical insights and design implications for developing multi-agent systems that support enriched media consumption experiences.

日本語まとめ
読み込み中…
読み込み中…