1. Home
  2. NOVA Information Management School
  3. Laboral - Data Science for Marketing
  4. Applied Network Analysis

Applied Network Analysis

Objectives

Often, structured data representations (e.g., tabular) are inadequate to capture the full intricacies of real-world systems. In particular, when the focus of study and analysis relies on the system's interconnectedness or the relationships between entities/actors/agents. In that context, Graphs provide a powerful abstraction that allows for the representation and study of the complex relationships between elements of a wide variety of systems ( e.g. , individuals and their social relationships in a population).

Stemming from discrete mathematics, Graphs have become a popular framework for tackling problems in many domains. For instance, in social sciences, Social Network Analysis (SNA) has been used to study social influence, the spread of innovations, and the formation of human capital; in Physics and Computer Sciences, complex networks have been key to understanding the functioning of complex systems; in Ecology, graphs have helped draw a picture about the interdependence between species and ecosystems and in showing their fragility and susceptibility to collapse; and in Financial Systems, networks have shed light on the systemic risk posed by different actors in financial institutions.

However, networks are not only a topic of academic and scientific interest. They are often used to visualize and understand interrelated structures in business and to optimize the storage and manipulation of unstructured data. They have been used to foster innovation, identify relevant individuals in populations, optimize teams and logistics infrastructures, and generate realistic what-if scenarios to support decision-making.

Processing network data typically requires a combination of graph analytics, data science, and machine learning. In Applied Network Analysis, students will first be introduced to the fundamental concepts of the science of Network Science and then to analytical techniques and applications. Students will learn how to formulate network-related questions from data and to bring value from their answers.

The curricular unit in Applied Network Analysis consists of 14 weekly classes.
Classes are divided into Lectures (theoretical) and Labs (practical)
All materials (syllabus, slides, readings, documentation) are shared through the dedicated Moodle page of this curricular unit

General characterization

Code

200268

Credits

7.5

Responsible teacher

Flávio Luís Portas Pinheiro

Hours

Weekly - Available soon

Total - Available soon

Teaching language

Portuguese. If there are Erasmus students, classes will be taught in English

Prerequisites

  • Intermediate knowledge of Python programming and the use of Python Pandas for data processing is recommended but not strictly necessary.
  • A basic understanding of algebra.
  • A basic understanding of Terminal/Shell commands is helpful.
  • Classes will be delivered in English. In that sense, students should have good comprehension and communication in the English language. 

Bibliography

[ Book.1 ] Baraba¿si, Albert-La¿szlo¿. Network Science. Cambridge University Press, 2016.
[ Book.2 ] Easley and Kleinberg, Networks, Crowds, and Markets: Reasoning about a highly connected world. Cambridge Univ. Press, 2010.
[ Book.3 ] Newman, Mark. Networks. Oxford university press, 2018.
[ Book.4 ] Jackson, Matthew O. Social and Economic Networks. Vol. 3. Princeton: Princeton university press, 2008.
[ Book.5 ] Van Steen, Maarten. "Graph theory and complex networks." An introduction 144 (2010).
Additional Reading materials communication articles will be shared weekly in Moodle to the students.  

Teaching method

The curricular unit is based on a mix of theoretical and practical lessons with a robust and active learning component. During each session, students are exposed to new concepts and methodologies, case studies, and the resolution of examples. Active learning activities (debates, quizzes, mud cards, compare-and-contrast, homework assignments) will foster students’ participation in the classroom, promoting peer learning and inciting discussion. 

Evaluation Elements:

EE1 - Participation in classroom activities (50%)

EE2 – Group Activity (50%).

Evaluation method

To successfully finish this curricular unit, students must score at least 9.5 points. The grading is divided into two seasons. Attendance in the second is optional for students who passed the curricular unit in the first season and can be used to improve their grades. 

First Season

The first grading season is dedicated to continuous evaluation, which includes the following components:

  • Practical Assignments (30%)
    • Three Assignments will be released at the end of the Labs and involve follow-up work at home (homework).
    • Activity to be done in Pairs, that cannot repeat.
    • Students must submit their solutions through Moodle
  • Readings and Discussions (20%)
    • Prepare the discussion of one of the papers during one of the Lectures;
    • The activity includes the presentation of a 5-minute to the class
    • Students must deliver a one-page summary of the reading, including a critical assessment of the results and their implications
  • Group Activity (50%)
    • Groups of 4/5 students
    • The Teaching Staff will propose the topics during the 8th week
    • Groups must be formed and with a selected group project by the start of the 8th week
    • Groups must provide a weekly point of situation until delivery (at the start of each lab/lecture)
    • Delivery is set for the 14th week of the academic semester (the last week of classes)
    • Delivery includes a 5-page report (including figures, references, and tables) and a 10-minute presentation
    • The report must include a title, authors’ names, 250-word abstract, statement of contributions, three keywords, references
    • Projects will be graded according to their relatedness to the topic, relevance of insights, and clarity
    • The date of presentations will be scheduled with the students during the second half of the semester
    • Each group will have 15 minutes to present their work, with 5 minutes for Q&A. For the presentation, each group must designate a single member to do the presentation

Second Season

The second grading season will take place in January and consists of a multiple-choice exam. The Exam consists of 40 questions. Correct answers count 0.5 points, and incorrect answers discount 0.2 points.

Subject matter

The curricular unit is organized into five Learning Units (LU):

  1.  – Fundamentals of Networks
  2.  – Network Analysis
  3.  – Advanced Network Analytics
  4.  – Applications of Network Analytics