July 11-13, 2022

  4.00 - 7.00 pm

 Registration must be done before May 31,2022.

 Room 54.003 - building 54. Àrea Tallers - Campus del Poblenou

 @comunicacioUPF

 @comunicacioupf

"Computational Analysis of Communication" given by Dr. Carlos Arcila Calderón

This workshop focuses on the application of the supervised and unsupervised texts analysis technique to real-time Twitter messages that can help social researchers to detect social trends or citizens’ attitudes. Participants will learn the very basis of programming in Python and will be able to retrieve tweets with Streaming and Rest APIs of Twitter. In addition, they will learn the mathematical representation of text (BoW, Embeddings), the basis of natural language processing (tokenizing, stemming, lemmatizing, stop words, frequency of words, etc.) and will learn lexicon-based sentiment analysis. The workshop will focus on supervised machine learning applied to unstructured data with different algorithms implemented in Scikit-Learn (naive bayes, logistic regression, support vector machines, etc.) and TensorFlow / Keras (RNN).

Schedule

Day 1

• Introduction to Computational Analysis of Communication
• Basic programming on Python 3.4
• Mathematical representation of text

Day 2

• Data retrieval of tweets with the Streaming and Rest APIs of Twitter
• Natural language processing with NLTK
• Lexicon-based sentiment analysis

Day 3

• Supervised machine learning and text classification
• Supervised sentiment analysis and visualization of tweets

Prerequisites

Some bases in statistics is desirable.

Software

We will use the language Python.

Places available

There are only 20 places available for the workshop.

Language

English/Spanish

References

• Van Atteveldt, W., Triling, D. & Arcila, C. (2022). Computational Analysis of Communication. Wiley.
• Bird, S., Klein, E., & Loper, E. (2009). Natural language processing with Python: analyzing text with the natural language toolkit. O'Reilly Media, Inc.
• Géron, A. (2019). Hands-on machine learning with Scikit-Learn, Keras, and TensorFlow: Concepts, tools, and techniques to build intelligent systems. O'Reilly Media, Inc..

Organised by UPF Media Labs and the Department of Communication at Pompeu Fabra University