Squiboon
Lead Research Organisation:
University of Bristol
Department Name: Computer Science
Abstract
The ISCF Healthy Ageing Follow on Fund 2023 is part of the Healthy Ageing Catalyst Award programme, funded by the UKRI Healthy Ageing Challenge and in collaboration with the US National Academy of Medicine's (NAM) Healthy Longevity Global Grand Challenge. With Zinc's programme of support, the Follow on Funding will be used to build upon previous Healthy Ageing Catalyst Award funding, with the aim of commercialising research in the use of conversational AI in care settings to tackle isolation and loneliness.
Much progress has been made in recent years with the use of Large Language Models, such as GPT-3, and these are now seeping into the mainstream and leading to a fundamental shift in the interaction between humans and computers.
However, further research is necessary if these advances are to be of benefit to the ageing population. In addition to the accessibility issues of those with deteriorating eyesight, hearing, memory, or other impairments, there are new challenges resulting from biases and deficiencies in the pre-trained models.
We'll be exploring novel and inclusive ways of communicating, using best practices in accessibility, using simple graphical interfaces in combination with natural, conversational audio.
We'll be testing conversational AI in group settings, exploring how speech idiosyncrasies of older adults, sound quality affect error rates in speech-to-text conversion, and the ability of speech recognition models to tell the speakers apart (diarisation).
We'll be looking at the emotional content of conversations and testing computers' abilities to track the emotional arc of a group discussion.
Finally, we'll be gathering new audio, visual and textual datasets to custom-train the artificial intelligence to be more inclusive and representative of older adults.
These insights will all be used to underpin additional product development that has arisen from an iterative design process with our steering group of older adults, following the previous Catalyst Award. This product will be deployed across retirement communities and care homes, to explore the effectiveness of the product in tackling loneliness in communities, as well as to identify and address implementation challenges.
Much progress has been made in recent years with the use of Large Language Models, such as GPT-3, and these are now seeping into the mainstream and leading to a fundamental shift in the interaction between humans and computers.
However, further research is necessary if these advances are to be of benefit to the ageing population. In addition to the accessibility issues of those with deteriorating eyesight, hearing, memory, or other impairments, there are new challenges resulting from biases and deficiencies in the pre-trained models.
We'll be exploring novel and inclusive ways of communicating, using best practices in accessibility, using simple graphical interfaces in combination with natural, conversational audio.
We'll be testing conversational AI in group settings, exploring how speech idiosyncrasies of older adults, sound quality affect error rates in speech-to-text conversion, and the ability of speech recognition models to tell the speakers apart (diarisation).
We'll be looking at the emotional content of conversations and testing computers' abilities to track the emotional arc of a group discussion.
Finally, we'll be gathering new audio, visual and textual datasets to custom-train the artificial intelligence to be more inclusive and representative of older adults.
These insights will all be used to underpin additional product development that has arisen from an iterative design process with our steering group of older adults, following the previous Catalyst Award. This product will be deployed across retirement communities and care homes, to explore the effectiveness of the product in tackling loneliness in communities, as well as to identify and address implementation challenges.
Organisations
Publications
Campbell S
(2024)
Psychological Digital Practice: the basics and beyond
Campbell, SE
(2024)
Psychological Digital Practice: the basics and beyond
| Description | As a result of this award, we were able to validate Squiboon as a successful and viable intervention at new sites and across new settings. This extended previous work where it had only been shown effective at the site where it was designed, enabled product developments to be identified and helped to raise awareness of the intervention. Another significant achievement was engaging with potential customers to help design the commercial offering, to maximise commercialisation success. The project also enabled us to conduct R&D around the integration of AI to improve Squiboon. Findings helped us to uncover significant bias in AI models relating to age, and work had begun to address these. The award has begun the integration of AI into Squiboon, and enabled us to identify what is needed to improve these parts of the system to deliver a viable user experience. Award objectives were met, which were to integrate AI into Squiboon, move towards commercialisation and develop the customer offering. It was also a key objective to validate if Squiboon was effective at other sites. The industry partner, Play Well For Life, has received funding from the Design Age Institute to use inclusive design approaches to develop a hardware product to improve the Squiboon experience, based on findings from this award. They have developed, in collaboration with a Bristol-based design agency, Kinneir Dufort, a hardware version of Squiboon, which is currently being tested with older adults. The research team from this award are exploring funding to develop the AI system based on findings from this award. |
| Exploitation Route | Retirement villages can take the findings from our work and implement improved ways for resident engagement and new resident activities based on conversation. Other researchers interested in ageing and community building can be informed by this project to help community service design Those interested in AI, ethics and assitive technology can be informed by our work |
| Sectors | Communities and Social Services/Policy Digital/Communication/Information Technologies (including Software) Healthcare |
| Description | Influenced creation of befriending service at a trial site |
| Geographic Reach | Local/Municipal/Regional |
| Policy Influence Type | Contribution to new or improved professional practice |
| Title | Transcripts of group conversations |
| Description | This contains the transcripts of the audio recordings from the group conversations, covering the topics Family, Travel, Tackling Loneliness and Reminiscing on the good times. It also includes pre/post ratings of mood and conversation experience |
| Type Of Material | Database/Collection of data |
| Year Produced | 2024 |
| Provided To Others? | Yes |
| Impact | This is informing the development of model training and insights into conversation dynamics |
| Title | Squiboon |
| Description | Squiboon is a conversational intervention to reduce loneliness, delivered in social care settings to alleviate staff burden and provide metrics for CQC reporting and reporting to families. Having been validated in the project, the next phases of development have been identified, to add conversation types and improve the AI system. We are seeking funding to do thisx |
| Type | Therapeutic Intervention - Psychological/Behavioural |
| Current Stage Of Development | Refinement. Non-clinical |
| Year Development Stage Completed | 2023 |
| Development Status | Actively seeking support |
| Impact | The co-design of the product and intervention has led to a notable reduction in loneliness for those involved in the process, and have led to new relationship and connections being made in the community settings. One trial site has now designed and implemented a new befriending service as a result of involvement in our trial . |
| Title | Annotation app |
| Description | An app to make annotation of audio recordings and transcripts more efficient |
| Type Of Technology | Webtool/Application |
| Year Produced | 2024 |
| Open Source License? | Yes |
| Impact | Reduced time spent on annotation to improve model accuracy |
| Company Name | Squiboon Limited |
| Description | |
| Year Established | 2023 |
| Impact | N/A |
| Description | "Patient" information sessions |
| Form Of Engagement Activity | Participation in an activity, workshop or similar |
| Part Of Official Scheme? | No |
| Geographic Reach | Local |
| Primary Audience | Patients, carers and/or patient groups |
| Results and Impact | Seven information sessions have been given at retirement villages and care homes to let people know about Squiboon, the project and to answer questions about the role of technology |
| Year(s) Of Engagement Activity | 2023,2024 |
| Description | BBC Radio Ulster interview |
| Form Of Engagement Activity | A broadcast e.g. TV/radio/film/podcast (other than news/press) |
| Part Of Official Scheme? | No |
| Geographic Reach | Regional |
| Primary Audience | Public/other audiences |
| Results and Impact | The project lead was interviewed on the Sunday morning Stephen Cainey BBC Radio Ulster programme, about Squiboon. The panel then debated the project and the points it raised related to AI for social support. This has an average audience of over 500,000 |
| Year(s) Of Engagement Activity | 2024 |
| Description | British Society of Gerontology annual conference 2023 presentation |
| Form Of Engagement Activity | A talk or presentation |
| Part Of Official Scheme? | No |
| Geographic Reach | International |
| Primary Audience | Professional Practitioners |
| Results and Impact | Delivered a presentation with our older adult co-researchers at the British Society for Gerontology Annual Conference, entitled "Community building through a co-design technology project: developing an ongoing partnership between the researcher and the co-researchers", which sparked interesting conversations and led to one of the co-researchers joining an Older Research Group, to support emerging older adult researchers |
| Year(s) Of Engagement Activity | 2023 |
| Description | Conference presentation |
| Form Of Engagement Activity | A talk or presentation |
| Part Of Official Scheme? | No |
| Geographic Reach | International |
| Primary Audience | Professional Practitioners |
| Results and Impact | Academic conference presentation |
| Year(s) Of Engagement Activity | 2023 |
| URL | https://www.britishgerontology.org/events-and-courses/bsg-annual-conference |
| Description | Demo at the LGA conference |
| Form Of Engagement Activity | Participation in an activity, workshop or similar |
| Part Of Official Scheme? | No |
| Geographic Reach | National |
| Primary Audience | Policymakers/politicians |
| Results and Impact | Demo at the LGA annual conference in Bournemouth |
| Year(s) Of Engagement Activity | 2023 |
| Description | Demo workshop |
| Form Of Engagement Activity | Participation in an activity, workshop or similar |
| Part Of Official Scheme? | No |
| Geographic Reach | National |
| Primary Audience | Professional Practitioners |
| Results and Impact | Squiboon was demo-ed at a workshop at the UKRI Healthy Ageing conference 2023, where participants (forty across two workshops) participated in a Squiboon session. We received useful insights about inclusive design, and this activity led to requests to use Squiboon for research evaluation work |
| Year(s) Of Engagement Activity | 2023 |
| Description | Design for Care Workshop |
| Form Of Engagement Activity | Participation in an activity, workshop or similar |
| Part Of Official Scheme? | No |
| Geographic Reach | International |
| Primary Audience | Professional Practitioners |
| Results and Impact | Three day workshop, Design for Care, in Belfast under the AHRC-funded workshop series |
| Year(s) Of Engagement Activity | 2023 |
| Description | Innovation pitch |
| Form Of Engagement Activity | A talk or presentation |
| Part Of Official Scheme? | No |
| Geographic Reach | National |
| Primary Audience | Industry/Business |
| Results and Impact | Pitch at Zinc Accelerator Investor day |
| Year(s) Of Engagement Activity | 2023 |
| Description | Innovation pitch |
| Form Of Engagement Activity | A talk or presentation |
| Part Of Official Scheme? | No |
| Geographic Reach | National |
| Primary Audience | Industry/Business |
| Results and Impact | Innovation pitch delivered at UKRI Healthy Ageing Annual Conference 2023 |
| Year(s) Of Engagement Activity | 2023 |
| URL | https://iuk.ktn-uk.org/news/innovation-pitch-zone-at-healthy-ageing-2023/ |
| Description | Pathfinder Talk |
| Form Of Engagement Activity | A talk or presentation |
| Part Of Official Scheme? | No |
| Geographic Reach | National |
| Primary Audience | Industry/Business |
| Results and Impact | Pathfinder project presentation to other pathfinder projects and supporters, before a discussion and workshop |
| Year(s) Of Engagement Activity | 2023 |
| Description | Steering Group meetings |
| Form Of Engagement Activity | A formal working group, expert panel or dialogue |
| Part Of Official Scheme? | No |
| Geographic Reach | Local |
| Primary Audience | Patients, carers and/or patient groups |
| Results and Impact | Following the original healthy ageing catalyst award, some of the participants involved in co-design wanted to continue their involvement. We formed a steering group with 10 participants, and we have met every month sept 2022 - aug 2023, and four times since then. Older adults on the steering group have contributed to research formulation, commercialisation plans, user testing, recruitment, study participation and product development. They also presented with us at the BSG annual conference in Norwich 2023, and one member has subsequently joined an emerging researchers in ageing group, specifically for older adult researchers in the ageing field |
| Year(s) Of Engagement Activity | 2023,2024 |