A Personalised Intervention Model for Improving
the Effectiveness of Driving-Behaviour Apps

Jawwad Baig

ABSTRACT: It can be argued that understanding driving behaviour and developing methods to improve it will lead to a decrease in accidents and improve citizen safety. At present, most of the work associated with driving behaviour is carried out by insurance companies who use mobile apps and telematic sensors to monitor driving behaviours. These companies are, mainly, capturing driving data to calculate annual premiums rather than to share that data with the drivers. On the academic side, the work focuses on feedback approach and real-time warnings systems. Both commercial and academic research does not consider the significant fact that all drivers are not the same; “one-size-fits-all” will not work.

Our Idea

This research investigates the scope of personalisation by factors such as age, gender, culture, country and type of driving (e.g. rural or urban) and its impact on driver behaviour. The aim is to improve the effectiveness of driving behaviour systems which can produce meaningful feedback to the drivers. Our model suggests that through personalisation, user-modelling and persuasive techniques such as regular feedback reports to drivers (showing their bad driving behaviours), it is possible to improve driving styles and eventually create improved driving behaviour changing systems. Another positive outcome of this model will be safer roads. We have conducted surveys, used focus groups and interviews to find out the types of driver and their preferences.

Research Questions (RQ)

  • RQ 1: (user modelling) – What information about drivers is useful for personalising feedback reports;
  • RQ 2: (user adaptation) – How should feedback reports be personalised based on the user model
  • RQ 3: (effectiveness) Are personalised reports more effective than non-personalised ones

Style of feedback reports

Hypothesis:

  • 1) From RQ1, we hypothesise that factors such as personality, affective state, past driving behaviours (to determine aggressive or non-aggressive driving), cultural backgrounds and ethnicity, rural and urban travel and country of residence are useful in personalising reports.
  • 2) From RQ2, we hypothesise that dividing drivers into categories (drivers by age groups, male/female drivers, experienced/non-experienced drivers, rural travel and urban travel, professional drivers etc) and distinguishing different behaviours which help tailor the feedback technology can increase the acceptance and effectiveness of the bad driving behaviours systems.
  • 3) From RQ3, we hypothesise that people who get personalised reports will have fewer unsafe driving incidents, including speeding, acceleration and harsh braking.

PhD Planned Activities

How will we develop the personalised model to make effective driving behaviour changing systems? Our priorities are:
User Modelling:

  • This task is related to research RQ1 and our approach will be to collect more data about drivers’ profiles e.g. age group, experienced/inexperienced, ethnicity, motorway travel, rural/urban travel, taxi driver, professional driver etc by arranging to survey at least 100 drivers. We will arrange surveys, focus groups and interviews so that we can define parameters to use in creating driver profiles.

Adaptation:

  • Conduct additional surveys based on our user modelling. We will ask drivers to explicitly tell us how they want reports to be personalised for them. We will use this as training data for a machine learning classifier (or predictive model) which predicts appropriate personalisation for new drivers based on their characteristics. This method will help us define the persuasive technique based on user modelling and personalisation to create effective behaviour-changing systems.

Evaluation:

  • Accurate feedback reports about the driving behaviours are key requirements to test the influence on changing behaviour. Similar to SaferDrive mobile app (Broun et at. 2018), we will conduct a larger evaluation at the end of the PhD with around 100 drivers using the app for six months.
  • We have plans to use our app in Pakistan and see how that can improve the driving behaviours there.

Paper doi link
DOI Link: https://doi.org/10.1145/3340631.3398680
UMAP Video