Social Media Analytics


Social media's rapid growth has given mass consumers a powerful tool to create knowledge and propagate opinions. Simultaneously, social media has created an unprecedented opportunity for organizations to engage in real-time interactions with consumers. Also, the size and richness of social media data have provided organizations an unusually deep reservoir of consumer insights to transform business and marketing operations.

The Social Media Analytics course will use a multidisciplinary approach that combines social network analysis, text mining, and data mining to help students grasp the analytics tools to leverage social media data. Students will be introduced and apply tools such as data collection, sentiment analysis, topic modeling, social network analysis, and influencers' identification.

General characterization





Responsible teacher

Vasco Miguel Lourenço Guerreiro Jesus


Weekly - Available soon

Total - Available soon

Teaching language

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


Although not required, it is recommended that students have basic knowledge of probability, statistics, graphs, and Python.


Teaching method

The curricular unit is based on blended learning. For almost all learning units, students will have access, before the class, to videos on the theoretical component. Students are required to watch those videos. In the presential class, students will be subjected to an evaluation quiz. Based on the quiz results, in a prescriptive manner, the instructor will discuss the topics that were not so well understood. Following the discussion of the topics, the instructor will give a practical class on the subject.

Evaluation method

Due to the application-based design of the course, evaluation is continuous.

All evaluation grades are on a scale of 0-20. The final course grade is calculated based on the following weights:

  • Completion of self-assessment survey: 2.5%
  • Quizzes: 40% (based on the top 5 quizzes grades - all quizzes will have the same weight)
  • Data collection individual project: 5%
  • Group membership submission (in the due deadline): 2.5%
  • Group project (minimum grade is 8.0):
    • Oral presentation: 10%
    • Materials (datasets, code, etc.) and report: 40%

There is no final exam. Instead, the group project is to be delivered and present at the 1st season exam date. If the minimum grade is not obtained, students may apply for resubmission on the 2nd season exam date.

All submissions should be made via Moodle. Submissions after the deadline will be rejected.


Subject matter

  • LU1. Introduction to Social Media Analytics
  • LU2. Introduction to Python
  • LU3. Data collection
  • LU4. Introduction to Text Mining
  • LU5. Graphs essentials
  • LU6. Network measures
  • LU7. Network models
  • LU8. Community analysis
  • LU9. Information diffusion
  • LU10. Influence and homophily


Programs where the course is taught: