10th EAI International Conference on Pervasive Computing Technologies for Healthcare

Research Article

Defining affective Identities in elderly Nursing Home residents for the design of an emotionally intelligent cognitive assistant

  • @INPROCEEDINGS{10.4108/eai.16-5-2016.2263875,
        author={Alexandra K\o{}nig and Aarti Aarti Malhotra and Jesse Hoey and Linda Francis},
        title={Defining affective Identities in elderly Nursing Home residents for the design of an emotionally intelligent cognitive assistant},
        proceedings={10th EAI International Conference on Pervasive Computing Technologies for Healthcare},
        publisher={ACM},
        proceedings_a={PERVASIVEHEALTH},
        year={2016},
        month={6},
        keywords={qualitative interviews; affective computing intelligent interactive systems; virtual assistant; prompting; support in adl; elderly care; dementia},
        doi={10.4108/eai.16-5-2016.2263875}
    }
    
  • Alexandra König
    Aarti Aarti Malhotra
    Jesse Hoey
    Linda Francis
    Year: 2016
    Defining affective Identities in elderly Nursing Home residents for the design of an emotionally intelligent cognitive assistant
    PERVASIVEHEALTH
    EAI
    DOI: 10.4108/eai.16-5-2016.2263875
Alexandra König1,*, Aarti Aarti Malhotra1, Jesse Hoey1, Linda Francis2
  • 1: University of Waterloo, Canada
  • 2: Cleveland State University, USA
*Contact email: akonig@uwaterloo.ca

Abstract

In this paper, we describe the first outcomes of the ACT@HOME research project which aims to develop an emotionally intelligent cognitive assistant (ICA) to engage and help older adults with Alzheimer’s disease (AD) to complete activities of daily living (ADL) more independently. To accomplish this, we carried out semistructured qualitative interviews with elderly nursing home residents in order to define their different affective identities, personalities and backgrounds. For this, a specific new interview tool was designed based on the principles of Affect Control Theory (ACT), a socio-cultural theory of affective interactions. The ICA will be programmed then to learn the different extracted affective identities (i.e., “personality”) of a person during an interaction, and will tailor prompts to specific individual’s needs’ in a way that ensures smoother and more effective uptake and response. Preliminary results of the first analysis of the interviews show that we can distinguish clearly between certain affective identities, such as for instance ‘the depressed lawyer’, or the ‘independent athlete’ etc. and thus, define their resulting preferences in a specific prompting style provided by the ICA.