Eye Tracker Assisted Search Engine

• Java
• Python
• Tobii Pro Eye-Tracker SDK
• QT
• Git
• Visual Studio Code

After an initial query asked by a user, search engines return a list of results composed of extracts (called snippets). The user then chooses the document that seems most interesting by clicking on the corresponding snippet, and then consults the document. If the document is not relevant, the user can return to the results page, and choose another document.
Eye-tracking can study how the user reads each snippet of the results page, and determine if some words are more particularly watched by the user. It is thus possible to extend the initial query of the user with these words, to send a new more precise query, and thus improve the search results without explicit intervention by the user.

For more detailed explanations here is a pdf explaining everything in more detail

Eye tracking assisted search engine

• Get the measures from the EyeTracker using its SDK (in Python)
• Connector between Python (EyeTracker) and Java (Backend)
• Creation of a GUI for an easier configuration of the Eye-Tracker device

• Detecting which point on the screen the user is looking at
• Determine which words the user reads and weight them (a longer fixation usually means more interest)

In yellow the position of the words and in blue the movement of the gaze, the size of a circle is proportional to the duration of the fixation.