Microcredential ekomex Introduction to Computational Social Science

This course provides a foundational building block in Computational Social Science (CSS), a field at the intersection of social science, data science, and social network analysis.

What Is This Course About?
The Digital Revolution remains largely untapped in the social realm without a computational mindset to extract and synthesize patterns from digital traces, such as political sentiment on social media. This course provides a foundational building block in Computational Social Science (CSS), a field at the intersection of social science, data science, and social network analysis. Students will explore how computational methods and tools can be applied to study complex social phenomena, including collective behavior in social networks, political fragmentation and discontent on social media, and spatial embeddedness in societal trends. Through a combination of theoretical insights and practical applications, the course offers an essential toolkit for using computational techniques to analyze social data.

Learning Goals

• Understand the core concepts and methodologies used in Computational Social Science.
• Build an integrated pipeline for data collection, data pre-processing, data-enrichment, and data visualization multimodal social data.
• Grasp key spatial theories and concepts relevant to social sciences such as spatial autocorrelation.
• Implement various text analysis methods, including sentiment analysis, topic modeling, and word embeddings, to address specific questions in social sciences from textual data.
• Apply computational tools to analyze the complexity of social and behavioral dynamics in Python environment.

Recommended Readings for the Course

• Foundation of Computational Social Science (focusing on digital data collection and experimentation in social research)
  Salganik, M. J. (2019). Bit by Bit: Social Research in the Digital Age. Princeton University Press.
• Social Network Analysis (examining network structures and their relevance to social systems)
  Borgatti, S. P., Everett, M. G., Johnson, J. C., & Agneessens, F. (2024). Analyzing Social Networks. SAGE Publications.
• Computational Geospatial Analysis (inquiring geospatial technique to enrich social context)
  Darmofal, D. (2015). Spatial Analysis for the Social Sciences. Cambridge University Press.
• Computational Text Analysis (using textual data for social science analysis)
  Grimmer, J., Roberts, M. E., & Stewart, B. M. (2022). Text as Data: A New Framework for Machine Learning and the Social Sciences. Princeton University Press.
• Social Complexity with Python (applying network-based computations using Python)
  Knickerbocker, D. (2023). Network Science with Python: Explore the networks around us using network science, social network analysis, and machine learning.

Assignments for the Course

• 4 daily formative assignments (not graded), applying the learned contents to your own research project / data.
• 1 final paper - own CSS application, ca. 2500 words - to be submitted within 3 weeks after completion of course.

Schedule

• Day 1
  09:00-10:30h - Course (An Overview of Computational Social Science)
  10.30-11:00h - Break
  11:00-12.30h - Course (Pipeline Design for Multimodal Social Data (Relational, Geospatial and Text)
  12:30-13:30h - Lunch break
  13.30-14.30h - Course (Project work)
  14:30-15:30h - Office hour
• Day 2
  09:00-10:30h - Course (Social Network Analysis)
  10.30-11:00h - Break
  11:00-12:30h - Course (Hands-on session)
  12:30-13:30h - Lunch break
  13.30-14.30h: Course (Project work)
  14:30-15:30h - Office hour
• Day 3
  09:0010.30h - Course (Computational Geospatial Analysis)
  10.30-11:00h - Break
  11:00-12.30h - Course (Hands-on session)
  12:30-13:30h - Lunch break
  13.30-14.30h - Course (Project work)
  14:30-15:30h - Office hour
• Day 4
  09:00-10.30h - Course (Computational Text Analysis)
  10.30-11h Break
  11:00-12.30h - Course (Hands-on session)
  12:30-13:30h - Lunch break
  13.30-14.30h - Course (Project work)
  14:30-15:30h - Office hour
• Day 5
  09:00-10.30h - Course (Social Complexity in the Digital Age)
  10.30-11:00h - Break
  11:00-12.30h - Course (Final Presentations)
  12:30-13:30h - Lunch break
  13:30-14:30h - Course (Final Presentations)
  14:30-15:30h - Office hour

Who Is Your Instructor?
Rafiazka Hilman is an Interdisciplinary Computational Social Scientist at the University of Amsterdam. Her works and academic activities are grounded on the intersection of network and data science, computational social science, and urban complexity science. I am particularly interested in expanding the scope of Artificial Intelligence (AI) for further scientific investigations related to Artificial Societies, including the dynamics of individuals, social interactions, and collective social dynamics.