Text Mining and Analysis

Semester 2 · 28852 · PhD Programme in Management · 1CP · EN

The course is designed for PhD students who want to learn the fundamentals of applied methods of text mining and analysis, with a straight focus on application. The course covers some broad theoretical traits of computational linguistics and focuses mainly on practical analysis processes of text mining and analysis, including some of the most frequent methods employed in this domain. Topics covered include text collection, basic techniques of text transformation and processing, syntactic and semantic analysis methods, text visualization, supervised and unsupervised classification methods.

Teaching Hours: 6, Prof. Loris Gaio, unitn
Lab Hours: 0
Mandatory Attendance: Required

Course Topics
During the course, some tools and software addressed to text analysis will be cited, although most applications will be developed using the Orange3 platform. At the end of the course, students will be able to conduct their own text analysis using a quite simple application environment. The course is suitable for PhD students enrolled in humanistic and social PhD programs who are interested in exploring theoretic fundamentals and application principles of text analysis and mining.

Teaching format
Frontal lectures, in-class discussion, exercises.

Educational objectives
By the end of this course, students will be able to: • Identify the relevant concepts and principles of text mining and analysis and their applications in research activities. • Select appropriate methods and strategies to apply text analysis to research projects requiring such kind of perspective. • Use tools and applications, such as Orange3, to collect, visualize, process, and analyze English texts

Assessment
Project work: sketch a brief proposal (max one page) for the application of text analysis on a research topic of interest; perform the analysis through an Orange3 workflow; comment results and most relevant evidence stemming from the analysis. A brief report and the Orange3 workflow must be delivered. NOTE: project works are valid for 1 academic year and cannot be carried over beyond that time-frame.

Evaluation criteria
Pass or no pass

Required readings

Readings will be provided during the course.

Supplementary readings

Readings will be provided during the course.

Download as pdf