Network Data Science
This course will introduce methods for analyzing and understanding the structure and function of networks, including social networks, web graphs, and sensor networks. The course will introduce students to the math and science of network analysis. Through real world examples, including analysis of their own networks, students will develop skills for describing and understanding the structure, patterns, and functionality of networks. Students will read classic and cutting edge articles and books about these topics and discuss their applicability to various network types. The class will culminate with a capstone project in which students will apply the analysis methods they have learned to understanding a particular question about a network they choose.
Objectives and Learning Outcomes
- Understand to the basic concepts of network analysis (Evaluation: problem sets)
- Collaborate with peers to apply these methods to a variety of networks (Evaluation: projects)
- Understand the link between qualitative and quantitative methods of network analysis (Evaluation: short analysis papers)
Course Outline
The course will be a combination of lecture, hands-on exercises, and discussion. Assignments will include the application of technologies to given tasks, analysis and writing of results on small projects, and a larger course capstone project that integrates the types of insights and analysis learned in class to study a specific type of network
- Network basics - structure, nodes and edges, centrality measures
- Network Visualization - how to represent and visualize networks
- Edge features - edge weight, tie strength, trust, interaction frequency, and other measures
- Network Propagation
- Small Worlds and Power Laws
- Temporal and Dynamic Networks
- Building networks - how to take observations and create network structure to analyze
Project
This course has a end-of-semester group project focusing on the fake news ecosystem. The project outline is here:Class Material
- Properties of Networks
- Network Analysis and Data Collection
- Random Graphs
-
Random Graphs, Power Laws, and Mixing
- Lecture Slides
- Homework, Answers
- Extra Notes
- Network Science, The Scale-Free Property by Barabasi
- Fast unfolding of communities in large networks by Blondel et al.
-
Diffusion, Cascades, and Clusters
- Diffusion Slides
- Clusters
- Jupyter Notebooks
- Diffusion Simulation – example networks for propagation and diffusion. You can modify diffusion parameters and explore how they affect propagation speed
- Diffusion Game – Interactive game for the class in which groups decide which nodes to infect or immunize, and we explore how each set of decisions affects propagation
- Modularity Examples – Examples for communities and spectral clustering
- Dynamics Networks
Books
- Analyzing the Social Web, by Jennifer Golbeck
- Please also get the Errata here.
Evaluation
- 50% Homework assignments (problem sets, papers, short analysis projects)
- 25% Class Participation (includes in-class exercises)
- 25% Final Project
Homeworks
Late policy: for assignments turned in a day or less late, you will lose 25% of your grade. Assignments more than a day late will not be accepted.
Class Participation
Class discussion will be an important part of this class running well. You will be assigned minimum participation requirements in the discussion boards, but you are encouraged to participate more. In class exercises are a required and important part of participation.
Academic Integrity
The University of Maryland, College Park has a nationally recognized Code of Academic Integrity, administered by the Student Honor Council. This Code sets standards for academic integrity at Maryland for all undergraduate and graduate students. As a student you are responsible for upholding these standards for this course. It is very important for you to be aware of the consequences of cheating, fabrication, facilitation, and plagiarism. For more information on the Code of Academic Integrity or the Student Honor Council, please visit http://www.shc.umd.edu.