ARIA e Interactive Access: projetando chatbots para idosos

• Carlos Nery Ribeiro USP
• Cynthya Letícia Teles de Oliveira USP
• Lucas Padilha Modesto de Araujo USP
• Kamila Rios da Hora Rodrigues USP
• Marcelo Garcia Manzato USP

DOI: https://doi.org/10.5753/webmedia_estendido.2024.243706

Resumo

Elderly individuals represent a significant portion of the population, and trends indicate that this number will increase at an accelerating rate. The elderly often face challenges when interacting with conversational systems, whether due to a lack of familiarity or age-related limitations, such as reduced visual acuity and dexterity. Therefore, it is essential to consider the needs of the elderly when designing these systems. In this work, we present the Assistente de Recomendação e Interação Acessível (ARIA), an accessible chatbot for the elderly that provides recommendations for cultural content, and Interactive Access, a set of guidelines for building accessible chatbots for the elderly. Performance and usability tests were conducted on both artifacts, based on Nielsen’s heuristics. The artifacts showed positive results, pointing the next steps for studies with elderly users.

Palavras-chave: Sistema conversacional, grandes modelos de linguagem, diretrizes, usabilidade, idosos

Referências

Lucas Padilha Modesto de Araujo. 2024. Diretrizes de apoio ao processo de construção de sistemas conversacionais de recomendação acessíveis: um estudo com usuários idosos. Dissertação de Mestrado. Instituto de Ciências Matemáticas e de Computação, Universidade de São Paulo, São Carlos. DOI: 10.11606/D.55.2024.tde-16042024-104313. Recuperado em 2024-08-19, de [link].

Jiahao Chen, Fu Guo, Zenggen Ren, Xueshuang Wang, and Jaap Ham. 2023. Human-chatbot interaction studies through the lens of bibliometric analysis. Universal Access in the Information Society (2023), 1–20.

Iván Esteban-Lozano, Álvaro Castro-González, and Paloma Martínez. 2024. Using a LLM-Based Conversational Agent in the Social Robot Mini. In International Conference on Human-Computer Interaction. Springer, 15–26.

Marco Furini, Silvia Mirri, Manuela Montangero, and Catia Prandi. 2020. Do conversational interfaces kill web accessibility?. In 2020 IEEE 17th Annual Consumer Communications & Networking Conference (CCNC). IEEE, 1 – 6.

Leonid Grinin, Anton Grinin, and Andrey Korotayev. 2023. Global Aging and our Futures. World Futures 79, 5 (2023), 536–556.

Taewan Kim, Seolyeong Bae, Hyun Ah Kim, Su-woo Lee, Hwajung Hong, Chanmo Yang, and Young-Ho Kim. [n. d.]. Evaluating and Auditing LLM-Driven Chatbots for Psychiatric Patients in Clinical Mental Health Settings. human performance 1, 5 ([n. d.]), 19.

Jakob Nielsen. 1995. How to conduct a heuristic evaluation. Nielsen Norman Group 1, 1 (1995), 8.

Jakob Nielsen and Rolf Molich. 1990. Heuristic evaluation of user interfaces. In Proceedings of the SIGCHI conference on Human factors in computing systems. 249–256.

Pragnya Ramjee, Bhuvan Sachdeva, Satvik Golechha, Shreyas Kulkarni, Geeta Fulari, Kaushik Murali, and Mohit Jain. 2024. CataractBot: An LLM-Powered Expert-in-the-Loop Chatbot for Cataract Patients. arXiv preprint arXiv:2402.04620 (2024).

Hasanin Mohammed Salman, Wan Fatimah Wan Ahmad, and Suziah Sulaiman. 2023. A design framework of a smartphone user interface for elderly users. Universal Access in the Information Society 22, 2 (2023), 489–509.

Ziqi Yang, Xuhai Xu, Bingsheng Yao, Ethan Rogers, Shao Zhang, Stephen Intille, Nawar Shara, Guodong Gordon Gao, and Dakuo Wang. 2024. Talk2Care: An LLM-based Voice Assistant for Communication between Healthcare Providers and Older Adults. Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies 8, 2 (2024), 1–35.

Yeliz Yücel and Kerem Rizvanoğlu. 2022. I am old too!: Understanding the Impact of Empathy and Voice Characteristics on Older Adults’ Perception of Voice Assistants. In 2022 IEEE International Conference on e-Business Engineering ( ICEBE ) . IEEE, 299–304.