Deploying social robots for multilingual accessibility: supporting newcomers and staff in public service spaces

Ashkenazi, Shaul (2026) Deploying social robots for multilingual accessibility: supporting newcomers and staff in public service spaces. PhD thesis, University of Glasgow.

Abstract

Millions of people around the world migrate each year for myriad reasons. Some move to find better job opportunities, others pursue education abroad, and many are forced to leave their countries due to conflict or persecution, such as refugees and asylum seekers. These newly arrived individuals face many challenges, such as navigating bureaucracy and accessing services. Language barriers can heighten stress during these interactions, especially when newcomers are not fluent in the host country’s language. In many cases, when support is offered in the host country, it is provided in the formal language of that country. Yet, studies on second-language interaction and access to services show that clients often prefer to use their native language. Communicating in their first language helps them express emotions, explain problems, and reflect on situations more effectively. Common workarounds include scheduling appointments with a translator, asking a friend to interpret, or relying on tools like Google Translate and hoping for accurate results. Multilingual social robots can be instrumental in providing support. However, care must be taken when developing any speech-based system, as it is crucial to take into account the linguistic needs of its target population. It is paramount not to perpetuate existing biases from the language and speech technology communities. To address these gaps, I have developed a multilingual support robot designed to work alongside human support workers who assist newcomers. The robot was deployed in public spaces, interacting with users in their native languages across two settings: 1) a student services center, and 2) a drop-in service for refugees and asylum seekers. Each design and deployment process was guided by consultations with key stakeholders to ensure contextual relevance. This work presents two tailored applications of the robot, each evaluated using complementary methods. First, I describe its use with international students at the University of Glasgow, assessed through a controlled lab study and an in-the-wild deployment. Second, I present its adaptation for refugees and asylum seekers at a charity drop-in service, informed by a co-design process with Syrian refugees and later evaluated through an in-the-wild study. Through these real-world applications, the thesis demonstrates the potential of multilingual support robots and provides practical guidelines for their deployment in public service environments.

• Item Type: Thesis (PhD)
• Qualification Level: Doctoral
• Subjects: Q Science > QA Mathematics > QA75 Electronic computers. Computer science
• Colleges/Schools: College of Science and Engineering > School of Computing Science
• Funder's Name: Engineering and Physical Sciences Research Council (EPSRC)
• Supervisor's Name: Foster, Dr. Mary Ellen, Stuart-Smith, Professor Jane and Skantze, Professor Gabriel
• Date of Award: 2026
• Depositing User: Theses Team
• Unique ID: glathesis:2026-86078
• Copyright: Copyright of this thesis is held by the author.
• Date Deposited: 25 Jun 2026 14:24
• Last Modified: 30 Jun 2026 08:38
• Thesis DOI: 10.5525/gla.thesis.86078
• URI: https://theses.gla.ac.uk/id/eprint/86078

Related URLs

• Conference proceeding
• Enlighten Publications Record
• Conference proceeding
• Conference proceeding
• Enlighten Publications Record
• Pre-print