The aim of this course is to present the main theoretical foundations and practical elements that will allow students to correctly conduct textual data analysis. Students will acquire a solid background on textual data extraction and analysis techniques from a theoretical and practical point of view. In particular, during the course students will:
The methods will be presented using the R software.
None
Lectures and laboratory sessions where students will be stimulated with active discussions and participation to create their own case study.
The evaluation will be based on:
• A final written test entailing theoretical questions and exercises to be solved with the R software.
• Assignments provided by the teacher (exercises, case studies, reports).
• Unstructured data and Big data: what they are, how to use them; characteristics of different data sources.
• Introduction to R software
• Working with strings: basic tools for managing with character strings (e.g. length computation, pattern recognition, regular expressions)
• Text data management: transformation from unstructured to structured, tokenization, cleaning, stemming, lemmatization.
• Text mining: introduction and different approaches; document representation; document synthesis; detection of distances between strings and text similarity.
• Sentiment analysis: design and development of methods for sentiment classification and polarity detection.
• Topic modeling: brief overview of methods for document content classification.
• Data extraction from the web: web scraping and API.
• Empirical applications with real data, with reference for example to data from library or museum websites, newspaper articles.
