The potential of Embodied Conversational Agents to stimulate adherence to eHealth interventions - Steps towards a more dynamical approach
Due to the COVID-19 crisis the PhD defence of Mark Scholten will take place (partly) online.
The PhD defence can be followed by a live stream.
Mark Scholten is a PhD student in the research group Psychology, Health & Technology (PGT). His supervisor is prof.dr. J.E.W.C. van Gemert-Pijnen from the Faculty of Behavioural, Management and Social Sciences (BMS).
Studies on Embodied Conversational Agents (ECA’s; ‘robots on screen’) have been conducted for more than two decades since the term was formally introduced in 1999. After all these years, ECA’s still hold the promise of more productive Human-Computer Interaction, but to date their results are mixed and inconclusive. Within this thesis it has first been investigated whether ECA’s can contribute to improving user adherence to self-guided eHealth interventions. Secondly, methodological issues with regards to ECA research have been discussed and solutions have been proposed.
To do so, this thesis took insights from a different domain into consideration; the Dynamical Systems Perspective (DSP). Note that the Dynamical Systems Perspective is a class of mathematical equations that describe time-based systems with properties such as complexity and non-linearity and can be simulated through Agent-Based Models. The principle of rapport is common to both the ECA and DSP domain and created the connection. Note that rapport is the experience of harmony between conversational partners. It is associated to the notion of ‘being in sync’.
The thesis demonstrated that the simulations run with the Agent-Based Model (ABM) were associated to fluctuations with regards to user motivation. The eHealth experiments run with the ECA showed small positive effects due to the ECA’s support.
By comparing behavioral states of eHealth user and ECA and assessing their degree of mirroring across multiple modalities (e.g., facial, lexical, postural), the state of the rapport building process can be gauged on a short-term and real-time basis. Moreover, the fluctuations in both the user’s motivational state and the user-ECA rapport state can be assessed during eHealth interventions, again on a short-term basis.
Finally, by comparing the patterns that arise from the short-term data with questionnaire data taken after the experiment, a combination of dynamical and static measurements can be realized.
It is expected that this approach will give the combined ECA and eHealth fields a new impetus and that the evidence for effective ECA’s can gain strength to live up to their promise.
