Session:「Task Communication」

Understanding Chatbot-mediated Task Management

論文URL: http://dl.acm.org/citation.cfm?doid=3173574.3173632

論文アブストラクト: Effective task management is essential to successful team collaboration. While the past decade has seen considerable innovation in systems that track and manage group tasks, these innovations have typically been outside of the principal communication channels: email, instant messenger, and group chat. Teams formulate, discuss, refine, assign, and track the progress of their collaborative tasks over electronic communication channels, yet they must leave these channels to update their task-tracking tools, creating a source of friction and inefficiency. To address this problem, we explore how bots might be used to mediate task management for individuals and teams. We deploy a prototype bot to eight different teams of information workers to help them create, assign, and keep track of tasks, all within their main communication channel. We derived seven insights for the design of future bots for coordinating work.

日本語のまとめ:

複数ツールを使ってタスク管理や連絡を取る。しかし、ツールの切替は非生産的なので、ボットを介してタスク管理しよう、というもの。 結果、利用者は「生産性が向上した」という声を得た一方で、チャットだと複数タスクへの対応が難しいという意見も。 合わせて、ボット設計の指標も提示している。

Face Value?

論文URL: http://dl.acm.org/citation.cfm?doid=3173574.3173965

論文アブストラクト: We are interested in increasing the ability of groups to collaborate efficiently by leveraging new advances in AI and Conversational Agent (CA) technology. Given the longstanding debate on the necessity of embodiment for CAs, bringing them to groups requires answering the questions of whether and how providing a CA with a face affects its interaction with the humans in a group. We explored these questions by comparing group decision-making sessions facilitated by an embodied agent, versus a voice-only agent. Results of an experiment with 20 user groups revealed that while the embodiment improved various aspects of group's social perception of the agent (e.g., rapport, trust, intelligence, and power), its impact on the group-decision process and outcome was nuanced. Drawing on both quantitative and qualitative findings, we discuss the pros and cons of embodiment, argue that the value of having a face depends on the types of assistance the agent provides, and lay out directions for future research.

日本語のまとめ:

AIや会話エージェントが発達しているが、実態の有無による効果は議論が分かれている。 そこで、グループ活動内にエージェントを導入し、実態の有無による変化を見た研究。 結果、実態の有無によるタスク遂行の差は余り見られなかったが、実態ありの場合はグループの協調作業に有効であることが見られた。

Inaccuracy Blindness in Collaboration Persists, even with an Evaluation Prompt

論文URL: http://dl.acm.org/citation.cfm?doid=3173574.3174068

論文アブストラクト: The tendency to believe and act on others' misinformation is documented in much prior work. This paper focuses on inaccuracy blindness, the tendency to take a collaborator's poor information at face value, which reduces problem-solving success. We draw on social psychological research from the 1970s showing that evaluative rating scales can prompt a change in perspective. In a series of studies, we prototyped and tested an evaluation prompt meant to encourage skepticism in participant detectives trying to identify a serial killer. In tests of the prototype, the prompt was partially successful in inducing skepticism (Exp. 1), but a larger study (Exp. 2) showed that, despite the evaluation prompt, participants' inaccuracy blindness persisted. This work, and the literature more generally, shows that the tendency to be misled by collaborators' inaccurate information remains a strong phenomenon that is hard to counteract and remains a significant challenge for the CHI community.

日本語のまとめ:

他者からの情報をそのまま受け取り、行動してしまうことはよくある。 これを「情報が論理的か」を判定することで防ぐことができるのでは、という仮説のもとシステムを作り実験をした研究。 結果、論理的かの判定の有無によるタスク遂行の差は見られなかった。 ここから、システム的に「誤った情報である」と提示したとしても、ユーザは無視してしまう可能性を指摘している。