From Information Seeking to Empowerment: Using Large Language Model Chatbot in Supporting Wheelchair Life in Low Resource Settings

Abstract

To tackle the lack of wheelchair service information and training in low and middle-income countries (LMICs), we deployed Wheelpedia, a WhatsApp chatbot powered by a large language model (LLM) as a design probe for 2 months to concretely explore how it can support wheelchair users and professionals in Nigeria and Kenya. Through 18 semi-structured interviews and analysis of 471 messages, we focused on not only Wheelpedia's acceptability and usability but also how users orient themselves with the probe, integrate its information, and manage trust with it. The findings revealed participants' overwhelming enthusiasm towards the chatbot's potential in education, fostering empowerment, and reducing social stigma. We discuss challenges like users' difficulty in formulating questions, unfamiliarity with the concept of chatbots, and requests for image output. This paper contributes valuable insights into the design implications and research opportunities for deploying LLM chatbots in low-resourced settings with complex accessibility needs.

Ähnliche Arbeiten