TY - GEN
T1 - Lessons Learned from Designing and Evaluating CLAICA
T2 - 28th International Conference on Intelligent User Interfaces, IUI 2023
AU - Kernan Freire, Samuel
AU - Niforatos, Evangelos
AU - Wang, Chaofan
AU - Ruiz-Arenas, Santiago
AU - Foosherian, Mina
AU - Wellsandt, Stefan
AU - Bozzon, Alessandro
PY - 2023
Y1 - 2023
N2 - Learning to operate a complex system, such as an agile production line, can be a daunting task. The high variability in products and frequent reconfigurations make it difficult to keep documentation up-to-date and share new knowledge amongst factory workers. We introduce CLAICA, a Continuously Learning AI Cognitive Assistant that supports workers in the aforementioned scenario. CLAICA learns from (experienced) workers, formalizes new knowledge, stores it in a knowledge base, along with contextual information, and shares it when relevant. We conducted a user study with 83 participants who performed eight knowledge exchange tasks with CLAICA, completed a survey, and provided qualitative feedback. Our results provide a deeper understanding of how prior training, context expertise, and interaction modality affect the user experience of cognitive assistants. We draw on our results to elicit design and evaluation guidelines for cognitive assistants that support knowledge exchange in fast-paced and demanding environments, such as an agile production line.
AB - Learning to operate a complex system, such as an agile production line, can be a daunting task. The high variability in products and frequent reconfigurations make it difficult to keep documentation up-to-date and share new knowledge amongst factory workers. We introduce CLAICA, a Continuously Learning AI Cognitive Assistant that supports workers in the aforementioned scenario. CLAICA learns from (experienced) workers, formalizes new knowledge, stores it in a knowledge base, along with contextual information, and shares it when relevant. We conducted a user study with 83 participants who performed eight knowledge exchange tasks with CLAICA, completed a survey, and provided qualitative feedback. Our results provide a deeper understanding of how prior training, context expertise, and interaction modality affect the user experience of cognitive assistants. We draw on our results to elicit design and evaluation guidelines for cognitive assistants that support knowledge exchange in fast-paced and demanding environments, such as an agile production line.
KW - chatbots
KW - cognitive assistant
KW - human-centered AI
KW - industry 5.0
KW - knowledge sharing
KW - knowledge-based AI
UR - http://www.scopus.com/inward/record.url?scp=85152123403&partnerID=8YFLogxK
U2 - 10.1145/3581641.3584042
DO - 10.1145/3581641.3584042
M3 - Conference contribution
AN - SCOPUS:85152123403
T3 - International Conference on Intelligent User Interfaces, Proceedings IUI
SP - 553
EP - 568
BT - IUI 2023 - Proceedings of the 28th International Conference on Intelligent User Interfaces
PB - ACM
Y2 - 27 March 2023 through 31 March 2023
ER -