The research project Gaze Mining was initiated by EYEVIDO GmbH and the WeST Institute of the University of Koblenz-Landau. It has a term of 2.5 years and started in January 2018.
The GazeMining project is funded by the program KMU-innovativ.
The aim of the research project GazeMining is to capture Web sessions semantically and thus obtain a complete picture of visual content, perception and interaction. The log streams of usability tests are evaluated using data mining. The analysis and interpretability of the data collected in this way is made possible by a user-friendly presentation, semi-automatic and automatic analysis procedures.
With our project we want to:
Full recording and advanced storage of subjects' sessions with interaction and eye tracking data.
Processing and evaluation of interaction and eye tracking data and visual content on the basis of data mining.
User-friendly data processing in an intuitive user interface for visualization and data analysis.
Support of usability professionals in evaluating the recorded data by automatic data analysis.
Approximately one billion Web pages are operated worldwide that want to address specific target groups and are under competitive pressure. Good usability, i. e. simple comprehensibility and intuitive operation, is essential for making information or goods accessible to visitors. The subject is not only of major importance in marketing and e-commerce. Due to the increasing number of online services offered by government agencies and authorities, usability is also a social issue, as it must also be possible for non-internet-related target groups to use it.
The analysis of eye tracking data, i. e. the eye behavior of users, is employed together with the analysis of interaction data (clicks, mouse movements, typing on the keyboard, scrolling, touch screen interaction) as a meaningful tool to understand user intuition and identify potential for improvement in usability studies. The goal of the research project GazeMining is to capture Web sessions semantically and thus obtain a complete picture of visual content, perception and interaction. The log streams from these usability tests are evaluated using data mining.
The analysis and interpretability of the collected data is made possible by (semi) automatic analysis methods and a user-friendly presentation. The main challenges in this area are the acquisition and analysis of highly dynamic Web page content and a variety of Web technologies and devices. To facilitate the further dissemination of the usability analyses, non-experts will also be enabled to analyze the eye tracking and interaction data. Usability experts of associated partners will accompany the project regarding the subject and will be involved in the development of the system and the evaluation. The market potential of GazeMining is very large, as the online market as well as the awareness of usability and user-centered development processes are constantly growing.
Start of the Research Project
1st January 2018
Definition of usage requirements in collaboration with usability experts
Presentation of the first results at the ETRA 2018
GazeMining is supported by a number of associated partners. They give valuable input to the project goals and evaluated the developed tools. Here a selection or our associated partners: