EXMOS: Explanatory Model Steering Through Multifaceted Explanations and Data Configurations

التفاصيل البيبلوغرافية
العنوان: EXMOS: Explanatory Model Steering Through Multifaceted Explanations and Data Configurations
المؤلفون: Bhattacharya, Aditya, Stumpf, Simone, Gosak, Lucija, Stiglic, Gregor, Verbert, Katrien
المصدر: Proceedings of the CHI Conference on Human Factors in Computing Systems (CHI '24), May 11--16, 2024, Honolulu, HI, USA
سنة النشر: 2024
المجموعة: Computer Science
مصطلحات موضوعية: Computer Science - Artificial Intelligence, Computer Science - Human-Computer Interaction
الوصف: Explanations in interactive machine-learning systems facilitate debugging and improving prediction models. However, the effectiveness of various global model-centric and data-centric explanations in aiding domain experts to detect and resolve potential data issues for model improvement remains unexplored. This research investigates the influence of data-centric and model-centric global explanations in systems that support healthcare experts in optimising models through automated and manual data configurations. We conducted quantitative (n=70) and qualitative (n=30) studies with healthcare experts to explore the impact of different explanations on trust, understandability and model improvement. Our results reveal the insufficiency of global model-centric explanations for guiding users during data configuration. Although data-centric explanations enhanced understanding of post-configuration system changes, a hybrid fusion of both explanation types demonstrated the highest effectiveness. Based on our study results, we also present design implications for effective explanation-driven interactive machine-learning systems.
Comment: This is a pre-print version only for early release. Please view the conference published version from ACM CHI 2024 to get the latest version of the paper
نوع الوثيقة: Working Paper
DOI: 10.1145/3613904.3642106
URL الوصول: http://arxiv.org/abs/2402.00491
رقم الأكسشن: edsarx.2402.00491
قاعدة البيانات: arXiv