Back to search

AAL-Active and Assisted Living Research and Development Programme

HANNAH

Alternative title: HANNAH

Awarded: NOK 0.11 mill.

The social networks deteriorate and fewer new contacts are made as we age. Older people often experience increasing loneliness and isolation. The goal of the Hannah Project is to investigate whether matchmaking algorithms can be used to establish new social networks in adulthood. The ambition of the Hannah Project is to support older adults in maintaining a strong social network by offering an innovative approach to establishing new social contacts through the development of a communication tool in the form of a speaker. In the project, seniors actively participate in the development of the communication tool through focus groups. We aimed to examine whether algorithms could have a broader approach and capture more dimensions that are relevant to human behavior. Can algorithms help older adults find new friendships from a broader social network? The concept pursues both social and emotional AI. How will coinciding variables such as topics, emotional temperament, cognitive mode, social skills, communication style, and other individual parameters like socioeconomic status, gender, health, and other variables that disrupt or maintain networks look? We will then use natural language processing techniques to identify which parameters should be used in the matchmaking process. The results will be applied in a cluster analysis to train a machine learning model. The research process is supported by principles of iterative user-centered approaches in design and ethical guidance related to best practices in user involvement. The project is now transitioning into a commercial product aimed at older adults.

Our focus groups clearly indicated the need for an easy tool to ineract socially. The match making system is under development.

Embracing the complexity of social networks in old age. In addition to the growing prevalence of age-related diseases, horizontal and social networks are shrinking, putting pressure on ageing societies. Integration into social networks promotes health and survival in old age. Social networks also act as moderators of disease and recovery histories of ageing-typical diseases such as heart disease, dementia and cancer. Objectives and insights to attain in the Small Collaborative Project (SCP) Develop a deeper understanding of the matchmaking process. What would the matching parameters look like, i.a. topics, emotional temperament, social style, cognitive mode, social skills, communication style, and other individual parameters like socioeconomic status, gender, health, and network-disturbing and network-sustaining variables. In this SCP, we aim to learn how-to-do good matches between users, which is vital to succeeding with our goals. Technological exploration We will use natural language processing techniques and preliminary information from psychologists to identify input parameters such as the person's topics of interest, emotional temperament, social style, cognitive mode, social skills, communication style, socioeconomic status, education level, gender, and age. The output will serve in a cluster analysis, which will train a machine learning (ML) model. The purpose of this model is to identify questions to be used by the matchmaking algorithm. Initially, we will use supervised learning, while we aim to build a fully unsupervised matchmaking algorithm capable of producing decision tree questions by itself. Our further aim is to develop a robust training set that improves the matchmaking algorithm from the very first beginning.

Funding scheme:

AAL-Active and Assisted Living Research and Development Programme