University of Glasgow
Deploying social robots for multilingual accessibility: supporting newcomers and staff in public service spaces
Abstract
dc:description.abstractMillions 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.
Degree
thesis:*- Level dc:type.qualificationlevel
- PhD
- Grantor dc:publisher.institution
- University of Glasgow
- Year dc:date.issued
- 2026
Author and committee
dc:creator, dc:contributor.*- Author dc:creator
-
- Ashkenazi, Shaul
Subjects
dc:subject × 1Rights
- Language dc:language
- en
Identifiers
dc:identifier.*- DOI dc:identifier.doi
- https://doi.org/10.5525/gla.thesis.86078