The life expectancy is on the rise, but with older age comes an increased chance of dementia. To make matters worse, dementia often copes with behavior-related issues such as anxiety. Many solutions are already in place to tackle these problems, but none have been as useful to the same extend regular social interaction have been. This is what Jelle tends to change by introducing the virtual Jelle. The virtual Jelle is a natural language processing application capable of having a conversation with a dementia patient whilst the patient thinks he or she is talking to an actual relative, therefore improving the status quo. 

The goal here is to show whether or not simulated phone conversations are indeed a plausible method for managing the mood of a person suffering from dementia. To do so, a Proof-of-Concept version of the virtual Jelle system has been build and tested on the mother of Jelle, who is suffering from middle-stage dementia. The results show that the virtual Jelle system is very successful in managing the mood of the dementia patients whilst also reducing the stress on the family member. The virtual Jelle, once completed, is expected to be a valuable asset in resolving behavioral problems associated with dementia.

For each time the virtual Jelle system is utilized, a brief report is written by the caretaker who operated the virtual Jelle system at that time. These reports are tracked for a total of three months in order to obtain sufficient information. The reports are reviewed and assessed by two independent annotators in order to reach an objective score.

After a period of three months, the virtual Jelle system has been used 28 times in total as an intervention. In 77% of the cases, the virtual Jelle system was able to improve the state of mind of Jelle’s mother at least slightly. Of this percentage, roughly 44% of the assessments claimed that the usage of the virtual Jelle system resulted in a great improvement in the mood of the patient. Therefore, it can be said that the virtual Jelle system is indeed useful in altering the emotion of people suffering from dementia.

Hani Al-Ers is a researcher in the field of human-machine interactions. He completed his PhD at the Delft University of Technology at the Interactive Intelligence group of the Faculty Computer Science (EEMCS). Philips Research in Eindhoven sponsored his project which was aimed at improving the user experience of Philips tv sets. He completed 2 post-docs at the Delft University of Technology, during which he managed international consortia on topics such as an improved quality of life for the elderly. Currently, he is conducting research in the field of health and education and he leads the Research Education activities at the Dutch Innovation Factory.