The internet has fundamentally changed people's lives. From a scientific perspective, human behavior has diversified significantly and is becoming increasingly volatile in the digital age. Therefore, self-reports in surveys cannot validly reflect the diversity and content of individual use of digital media. As a reaction, web tracking, i.e., the collection of the web browsing behavior of study participants through web browser plugins, has emerged as a new data collection method. The collection and linkage of web tracking with panel surveys offers the most comprehensive methodology for explaining and investigating online media use and information-seeking behaviors and their effects.

Still, web tracking data poses theoretical, infrastructural, ethical, and legal challenges for researchers. When data is successfully acquired, efficient and scalable pipelines need to be produced to handle the resulting large datasets. And before starting an analysis, researchers have to take manifold preprocessing and data aggregation decisions that need to be theoretically justified and transparently reported.

This workshop introduces participants to the preprocessing and analysis of web tracking data. Participants will get to know foundational studies, theories, and methods for handling web tracking data. We will show how to navigate challenges and how to devise appropriate research designs in computational social science. Primarily, the course will be application oriented. Participants will familiarize themselves with the main preprocessing steps and routines when handling web tracking data and learn how to implement these in R. The hands-on applications will be based on example web tracking datasets collected by GESIS. Equipped with this theoretical and methodological toolkit, participants will be able to develop their own research projects based on web tracking data and can discuss research ideas with the lecturers.

 

Organizational structure of the course

The workshop will be structured around three hours of classroom instruction and three hours of hands-on exercises per day. We will mix these elements, aiming to create an engaging and varied learning environment. The instruction sessions will introduce theories, concepts and methods. The hands-on sessions will be structured around exercises and group work. The instructors will support work on assignments and exercises, structure and facilitate discussions within group work assignments and be available for individual consultations on participants' projects.

You will find the course useful if:

By the end of the course, you will:

Software and hardware requirements

Participants should have the latest versions of R and RStudio installed on their own laptop.