Abstract:As the utilization of language models in interdisciplinary, human-centered studies grow, the expectation of model capabilities continues to evolve. Beyond excelling at conventional tasks, models are recently expected to perform well on user-centric measurements involving confidence and human (dis)agreement -- factors that reflect subjective preferences. While modeling of subjectivity plays an essential role in cognitive science and has been extensively studied, it remains under-explored within the NLP community. In light of this gap, we explore how language models can harness subjectivity by conducting comprehensive experiments and analysis across various scenarios using both fine-tuned models and prompt-based large language models (LLMs). Our quantitative and qualitative experimental results indicate that existing post-hoc calibration approaches often fail to produce satisfactory results. However, our findings reveal that personality traits and demographical information are critical for measuring subjectivity. Furthermore, our in-depth analysis offers valuable insights for future research and development in the interdisciplinary studies of NLP and cognitive science.
Abstract:Parenting brings emotional and physical challenges, from balancing work, childcare, and finances to coping with exhaustion and limited personal time. Yet, one in three parents never seek support. AI systems potentially offer stigma-free, accessible, and affordable solutions. Yet, user adoption often fails due to issues with explainability and reliability. To see if these issues could be solved using a co-design approach, we developed and tested NurtureBot, a wellbeing support assistant for new parents. 32 parents co-designed the system through Asynchronous Remote Communities method, identifying the key challenge as achieving a "successful chat". Aspart of co-design, parents role-played as NurturBot, rewriting its dialogues to improve user understanding, control, and outcomes. The refined prototype evaluated by 32 initial and 46 new parents, showed improved user experience and usability, with final CUQ score of 91.3/100, demonstrating successful interaction patterns. Our process revealed useful interaction design lessons for effective AI parenting support.
Abstract:We present a Research-through-Design case study of the design and development of an intimate-space tangible device perhaps best understood as a socially assistive robot, aimed at scaffolding children's efforts at emotional regulation. This case study covers the initial research device development, as well as knowledge transfer to a product development company towards translating the research into a workable commercial product that could also serve as a robust research product for field trials. Key contributions to the literature include: 1. sharing of lessons learned from the knowledge transfer process that can be useful to others interested in developing robust products, whether commercial or research, that preserve design values, while allowing for large scale deployment and research; 2. articulation of a design space in HCI/HRI--Human Robot Interaction--of intimate space socially assistive robots, with the current artifact as a central exemplar, contextualized alongside other related HRI artifacts.