Lessons Learned from an Eye Tracking Study for Targeted Advertising in the Wild
Melanie Heck, Janick Edinger, Christian Becker · 2022 IEEE International Conference on Pervasive Computing and Communications Workshops and other Affiliated Events (PerCom Workshops) · 2022
With the ambitious objective in mind to assess the validity of gaze-based interest prediction and test its application for targeted advertising on a self-order terminal, we set out to conduct a user study at a fast food restaurant. We recorded the customers’ eye movements while they were placing their order, and used the collected data to infer which information about the meals they were interested in. We then wanted to test whether the predictions can be used to display targeted advertisements, and influence the customers’ purchase intention for a complementary product. The results did not corroborate the hypothesized relationship between visual attention and interest. However, due to the multiplicity of underlying assumptions, we were unable to identify whether a link does indeed not exist, or whether the result was caused by the experimental setup.In this paper, we describe the design and results of our user study, and discuss our lessons learned. Our observations shall guide other researchers to avoid these common pitfalls.