eprintid: 10199622 rev_number: 11 eprint_status: archive userid: 699 dir: disk0/10/19/96/22 datestamp: 2024-11-07 16:15:25 lastmod: 2024-11-07 16:15:25 status_changed: 2024-11-07 16:15:25 type: proceedings_section metadata_visibility: show sword_depositor: 699 creators_name: Mo, Wen creators_name: Singh, Aneesha creators_name: Holloway, Catherine title: From Information Seeking to Empowerment: Using Large Language Model Chatbot in Supporting Wheelchair Life in Low Resource Settings ispublished: pub divisions: UCL divisions: B02 divisions: B04 divisions: C07 divisions: D05 divisions: F70 divisions: F48 keywords: Assistive Technology, Information Seeking, Chatbot, Large Lan�guage Model Chatbot, Accessibility, Disability, Wheelchair, Low and Middle-Income Countries, Informal Setting, Nigeria, Kenya note: This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike International 4.0 License. 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. date: 2024-10-27 date_type: published publisher: ACM official_url: https://doi.org/10.1145/3663548.3675609 oa_status: green full_text_type: pub language: eng primo: open primo_central: open_green verified: verified_manual elements_id: 2329538 doi: 10.1145/3663548.3675609 isbn_13: 979-8-4007-0677-6 lyricists_name: Holloway, Catherine lyricists_name: Singh, Aneesha lyricists_name: Mo, Wen lyricists_id: CSHOL54 lyricists_id: ASING59 lyricists_id: WMOXX44 actors_name: Mo, Wen actors_id: WMOXX44 actors_role: owner full_text_status: public pres_type: paper publication: The 26th International ACM SIGACCESS Conference on Computers and Accessibility volume: 3 event_title: ASSETS '24: The 26th International ACM SIGACCESS Conference on Computers and Accessibility book_title: The 26th International ACM SIGACCESS Conference on Computers and Accessibility citation: Mo, Wen; Singh, Aneesha; Holloway, Catherine; (2024) From Information Seeking to Empowerment: Using Large Language Model Chatbot in Supporting Wheelchair Life in Low Resource Settings. In: The 26th International ACM SIGACCESS Conference on Computers and Accessibility. ACM Green open access document_url: https://discovery.ucl.ac.uk/id/eprint/10199622/4/Mo_3663548.3675609.pdf