The course aims at providing theoretical and methodological knowledge about digital text analysis and automatic language processing.
The course illustrates the basics of textual and computational linguistics as well as the tools and methods of analysis of written/spoken texts.
At the end of the course, the student will be able to use the computational technologies for the statistical analysis and classification of texts. Students will also acquire the ability to understand how linguistic choices can make communication more effective in the digital contexts, and how the use of digital technologies is changing language and language processing.
Frontal lessons, exercises, laboratory sessions and discussion of scientific articles.
Laboratory sessions will serve as a tool to support the acquisition of theoretical content and practical skills for text analysis.
Particular emphasis will be given to discussion and direct dialogue with the students, who will be invited to formulate proposals for further study or debate.
The examination takes place orally and the evaluation is expressed in thirtieths. Students will be required to analyse texts or linguistic phenomena by means of the technologies/methods learnt during the course.
The acquisition of the course content as well as argumentation skills and mastery of specialistic terminology will be tested.
Attending students: Project work + oral discussion and presentation (at the end of the course)
Non attending students: Traditional oral exam concerning the topics of the course (during exam sessions)
The course illustrates the tools and methods for (written and spoken) text analysis and automatic language processing.
It describes (i) the data search methodologies for the extraction of lexemes, (ii) the computational technologies for the statistical analysis of the lexicon, of co-occurrence matrices and of the distributional properties of words, for the representation and modulation of senses in context, as well as (iii) tools for the classification of textual content through the automatic extraction of opinions, subjectivity and discourse polarity information.
Specifically, the teaching programme includes the presentation and discussion of the following topics:
-) Linguistic data and their representation
-) Written/spoken texts and their digital coding
-) Mark-up coding
-) Methods and techniques of digital text analysis
-) Basics of statistics. The concepts of frequency and probability.
-) Corpus studies
-) Automatic corpus annotation
-) Automatic language processing
-) Text analysis tools -) Interpretation of text data
-) Natural Language Processing tasks
-) The extraction of opinion information: Sentiment Analysis
There are no syllabus differences between attending and non-attending students.
The course will take place in the first semester (subperiods I-II).
