BLISS: Behaviour Based Language-Interactive Speaking Systems
The availability of large amounts of personal data (Big Data) and the enormous improvements recently made in language and speech technology offer new opportunities for self-management and empowerment of clients in healthcare. This research proposal is based on a broad definition of health and well-being as happiness and aims to develop an interactive, Dutch speaking system that helps people increase their well-being and happiness.
The idea is to search large amounts of clients' personal data (texts, interviews, dialogues) to extract information about their health and well-being and to find out what makes them happy. To make this possible, technology is being developed that can extract relevant information from Dutch texts and audio recordings. This information can then be used to design computer programs that can communicate with people in accessible, spoken Dutch to support them in their daily activities and manage their health and well-being. The information from Big Data can be used to personalize the system for individual clients so that it takes into account personal needs and background.
This research proposal is innovative in several ways. Research with Big Data has so far been mainly based on written data, while this project also uses spoken interviews, because these are now collected much more than written questionnaires. The advantage is also that spoken data contains much more information than texts (such as intonation, emphasis, hesitations, etc.). Furthermore, this research is new because low-threshold computer programs are being developed that can speak to people so that they are also suitable for the low-educated, visually impaired and people with disabilities. Also new is that the communication is intelligent and personalized, so that people are ultimately helped to take control of their own health, well-being and happiness. Finally, this research is innovative because the technology is developed for the Dutch language, because it is important for clients that they are addressed in their mother tongue.
In order to test whether everything works well and whether the developed system can actually support people, the developed technology will be embedded in existing applications for day care and calendar management that use gamification and that are already being used in healthcare. These enriched gaming applications will then be evaluated by large numbers of users.
This research will yield various results. Firstly, important Dutch-language technology for analysing large amounts of texts and recordings about and from clients and extracting relevant information about their health and well-being. This technology can also be used for other purposes, such as improving a speech recognition system. Furthermore, this project also provides knowledge about an interactive system that can speak in Dutch, understand their answers and have important information about the clients that they can use to improve their well-being, so that they are in control. This system can also be used for other applications in healthcare. Important results are of course also the knowledge and insights that will be obtained about what works best for whom.
Organisatie: Radboud Universiteit
Sign up for our newsletter and stay informed of the latest news Commit2data