Social Media Mining
A.Y. 2024/2025
Learning objectives
The learning objective of the course is provide students with the main concepts methods and algorithms of social network analysis.
Expected learning outcomes
Students will be able to apply the concepts, methods and models to analyze, model and visualize data from social networks to get valuable insights. At the end of the course students will be able to design and carry out large-scale social network analysis studies.
Lesson period: Second semester
Assessment methods: Esame
Assessment result: voto verbalizzato in trentesimi
Single course
This course can be attended as a single course.
Course syllabus and organization
Single session
Responsible
Lesson period
Second semester
Course syllabus
The course presents fundamental concepts, measures, and effective algorithms for social network analysis and mining
Theory:
Networks models
Connected componentes
Node degree
Scale-free networks
Clustering coefficient
Small-world networks
Node Similarity
Assortativity
Community detection
Information diffusion
Link prediction
Machine learning for social media mining: an introduction
Lab:
Data gathering: social media API
Network visualization - Gephi
Network analysis - NetworkX
Link prediction
LLM per social media mining
Bot detection
Theory:
Networks models
Connected componentes
Node degree
Scale-free networks
Clustering coefficient
Small-world networks
Node Similarity
Assortativity
Community detection
Information diffusion
Link prediction
Machine learning for social media mining: an introduction
Lab:
Data gathering: social media API
Network visualization - Gephi
Network analysis - NetworkX
Link prediction
LLM per social media mining
Bot detection
Prerequisites for admission
The course requires knowledge of basic computer science principles and familiarity with linear algebra and statistics.
Teaching methods
Lectures and in-class lab exercizes.
Teaching Resources
Sito Myariel
Recommended texts:
Social Media Mining, Reza Zafarani, Mohammad Ali Abbasi, Huan Liu, Cambridge University Press, 2014
Albert-LászlóBarabási: "Network Science"
D. Easley, J. Kleinberg, "Networks, Crowds, and Markets: Reasoning About a Highly Connected World"
Recommended texts:
Social Media Mining, Reza Zafarani, Mohammad Ali Abbasi, Huan Liu, Cambridge University Press, 2014
Albert-LászlóBarabási: "Network Science"
D. Easley, J. Kleinberg, "Networks, Crowds, and Markets: Reasoning About a Highly Connected World"
Assessment methods and Criteria
The exam consists of a written test on the theory of the course and the development of a laboratory project that will be discussed in an oral exam.
In the two-hour written test, students are asked to solve some exercises and summarize some of the topics presented in the course.
The laboratory project consists of a social media analysis project designed by the student.
The exam ends with an oral discussion, which focuses on the presentation of the laboratory project followed by a discussion on the salient elements of the project itself and on the applied methodologies.
At the end of the oral test, the overall evaluation is expressed in thirtieths, taking into account the following aspects: the degree of knowledge of the topics, the ability to apply knowledge to the resolution of concrete problems, and the ability of critical reasoning. The written and oral parts have the same weight in the final evaluation.
In the two-hour written test, students are asked to solve some exercises and summarize some of the topics presented in the course.
The laboratory project consists of a social media analysis project designed by the student.
The exam ends with an oral discussion, which focuses on the presentation of the laboratory project followed by a discussion on the salient elements of the project itself and on the applied methodologies.
At the end of the oral test, the overall evaluation is expressed in thirtieths, taking into account the following aspects: the degree of knowledge of the topics, the ability to apply knowledge to the resolution of concrete problems, and the ability of critical reasoning. The written and oral parts have the same weight in the final evaluation.
INF/01 - INFORMATICS - University credits: 12
Laboratories: 48 hours
Lessons: 72 hours
Lessons: 72 hours
Professors:
Gaito Sabrina Tiziana, Zignani Matteo
Shifts:
Professor(s)
Reception:
by appointment via email
office (Celoria 18, floor VII) or online (covid emergency)