π€ AI Summary
This study investigates how to design personalized AI writing assistants tailored to usersβ personality differences to enhance human-AI collaboration effectiveness. Through participatory co-design workshops integrating personality assessments and iterative prototype feedback, the research systematically examines the divergent functional, interactional, and visual preferences of writers across personality types. It pioneers the integration of personality traits into the AI writing tool design process and introduces the concept of βhuman-AI team matching,β emphasizing the critical role of cognitive and interpersonal needs in shaping collaborative experiences. Findings reveal both shared foundational requirements among writers and pronounced personality-driven preferences, demonstrating that personalized AI companions significantly improve user engagement and collaborative efficiency.
π Abstract
The growing popularity of AI writing assistants creates exciting opportunities to support diverse writers. This study examines how personality shapes expectations for AI writing companions and how personality-informed design can enhance human-AI teaming in writing. Through exploratory co-design workshops with 24 writers representing different personality profiles, we elicited values and design ideas for AI writing companions spanning functionality, interaction dynamics, and visual representation. These insights informed two contrasting prototypes reflecting distinct writing orientations, used as design provocations in review-and-refinement workshops with eight participants to prompt reflection on fit, priorities, and writing practices. Our findings reveal both shared foundational needs across writers and meaningful personality-driven preferences that influence how writers engage with AI. This work underscores the importance of team matching in human-AI collaboration and demonstrates how aligning AI companions with individual cognitive and interpersonal needs can improve engagement and perceived collaboration effectiveness.