SOCIAL MEDIA DATA ANALYSIS

Academic Year 2023/2024 - Teacher: FRANCESCO RAGUSA

Expected Learning Outcomes

Knowledge and understanding: The student will acquire the knowledge of the concepts behind social media and the analysis of their data.
Applying knowledge and understanding: The student will acquire the practical skills for implementing systems to analyze data extracted from social media.
Making judgments: Through the laboratories and the projects assigned to the students, they will be able to independently develop solutions that can solve the basic problems which could arise in the world of work.
Communication skills: the student will acquire the necessary communication skills and the appropriate use of technical language in the general field of social media and data analysis.
Learning skills: The course aims to delve into theories and techniques useful for the creation of systems for the analysis of multimedia data (images, text, tags, metadata) present in social media. The students will acquire knowledge and skills useful for the analysis of large amounts of multimedia data present in social media. The knowledge acquired will be applied through laboratory and projects. The oral test for passing the exam will be useful for developing the appropriate communication skills.

Frontal lessons, laboratory lessons and seminars.

Fundamental notions from the following courses will be used:

Recommended.

Social media: definition, features and short history
APIs and libraries for extrapolation, processing, and visualization of social media data, Web Scraping
Introduction to the text analysis, regular expressions, tokenization, speech tagging, named entity recognition, lemmatization, bag of words model, sentiment analysis, word embeddings
Information retrieval, evaluation measures. Nearest Neighbor Search.
Prediction and classification problems, evaluation measures. MAP and Naive Bayes.
Image popularity estimation through linear regression.
Recommender systems
Sentiment Analysis on social media using VADER (Valence Aware Dictionary for Sentiment Reasoning).
Introduction to the image analysis on social media: Bag of Visual Words model.
Python libraries for the analysis of data coming from social media.
Seminars focused on social media (ex. privacy, law, psychological).

R. Zafarani, M. A. Abbasi, H. Liu, Social Media Mining - An Introduction, Cambridge University Press, 2014
James, G., Witten, D., Hastie, T., & Tibshirani, R. (2013). An introduction to statistical learning. New York: springer
C. Bishop, Pattern Recognition and Machine Learning, Springer, 2006
E. Alpaydin, Introduction to Machine Learning, The MIT Press, 2009
Y. Bengio, I. J. Goodfellow, A.Courville, Deep Learning, Book in preparation for MIT Press, 2015
Duda, P. E. Hart, D. G. Stork, Pattern Classification (2nd ed.), Wiley, 2000
R. Szeliski, Computer Vision: Algorithms and Application, Springer 2010
J. Leskovec, A. Rajaraman, J. D. Ullman, Mining of Massive Datasets, Cambridge University Press, 2011
Y. Bengio, I. J. Goodfellow, A.Courville, Deep Learning, Book in preparation for MIT Press, 2015