In case the course is not able to convene face-to-face, lectures and final presentations will be held by remote video (i.e. "Distance Mode"). Students will have the option to present their final projects either on a livestream or by pre-recorded video. The mid-term assignment and the supporting materials for the final project will be submitted and graded the same way whether on-campus activity is limited or not.

This course aims to explore fundamental topics of the social sciences using computational methods including agent-based modeling/simulation, network science, text analysis, and machine learning. Participants will learn how to apply and evaluate these methods to measure and understand social and economic outcomes. Students will also gain experience in various methods to collect data from the web. We will use the Python programming language and the Jupyter Notebook environment.

After completing this course students will have an understanding of the opportunities and pitfalls of studying social behavior using data collected from the web. Students will understand how to formulate and test hypotheses using digital trace data. Students will apply mathematical and statistical tools to support design making. Completing this course will contribute to the students’ ability to efficiently work and communicate in a team to deliver interpretable and practical information from big data. They will also reinforce their understanding of ethical data analysis and potential biases in data-driven analyses of social phenomena.

The rules on the attendance of a Continuous Assessment Course (PI) apply. See the dedicated page on the WU portal for further information.

Each course session will consist of a lecture introducing a specific topic and methodology and a hands-on programming lab, implementing the main ideas of the lecture in code.

The final grade will be composed of:

- (30%) a mid-term assignment of programming and analysis tasks, to be submitted individually as an annotated Jupyter Notebook

- (60%) a final project completed in pairs and presented during the final meeting. Besides the final presentation the students will submit an annotated Jupyter Notebook replicating their analysis. Topics will be distributed in the second course meeting. 

- (10%) to be earned by active participation during the lectures and practical sessions.

In case of "scenario B", the final project can be presented either via live remote video or by a pre-recorded video. The participation points (10%) will be granted by participation (not correctness) in short quizzes during the lecture.

Successful conclusion of the course 1 of SBWL Data Science.

Please be aware that, for all courses in this SBWL, registration is only possibly for students who successfully have completed the entry course (Einstieg in die SBWL: Data Science).