Projektinformation

Beskrivning

Programming has always been a cognitively demanding exercise. In particular, modern software development requires a collective effort of programmers and the orchestration of a rather complex programming infrastructure. With the emergence of disruptive technology, e.g., AI and quantum computing, the programming prac- tice is undergoing a change, facing some uncertainty that we may not be able to predict but can only imagine.

With the maturity of eye-tracking in the past decades and the integration of eye- trackers into everyday consumer electronic devices such as Alienware’s laptops and Apple’s Vision Pro, we are optimistic it will eventually make its way into everyday use just as touchpad, camera, and microphone.

Therefore, we see an opportunity to design eye-tracking based assistance to support programmers. Given programmers spend a large amount of their time reading and understanding code, which heavily relies on eyes, we deem this to be a promising problem domain where eye-tracking can be of assistance.

To explore this inquiry, we undertook two mapping studies to establish the problem and solution constructs. We then surveyed a group of professional developers to understand this representative cohort of our prospective users and gather concrete, situated problems from them. We conducted these studies under the guiding design science model for empirical software engineering which centers on a problem-solution pair.

We found eye-tracking so far is used mostly for education-oriented studies in the research community focused on programming or software development. There is a need to bring it closer to practitioners. The gaze data produced by eye track- ers has been explored with a collection of machine learning techniques. However, these models were trained with small samples that might carry bias and insufficiency. Contemporary machine learning techniques may be able to compensate for that. Developers have already adopted AI assistance, they are more positive about it despite there is room for greater accuracy. As eye-tracking is relatively novel to them, most developers are unsure about how it can help them.

We will practice designing with programmers to develop and evaluate our proof of concept and believe much further work can be done by applying machine learning to gaze data, which may lead to integration into our system.
StatusPågående
Gällande start-/slutdatum2021/04/012026/03/31

FN:s Globala mål

År 2015 godkände FN:s medlemsstater 17 Globala mål för en hållbar utveckling, utrota fattigdomen, skydda planeten och garantera välstånd för alla. Projektet relaterar till följande Globala mål:

  • SDG 3 – God hälsa och välbefinnande
  • SDG 4 – God utbildning
  • SDG 9 – Hållbar industri, innovationer och infrastruktur