Text Mining

About

This course proposes an introduction to text mining, considering the intersection between big data and linguistics. Participants will study and apply techniques and models of Natural Language Processing (syntax, semantics and data preprocessing), dictionary approaches (existing dictionaries and customized ones), supervised learning (classifications of documents into predefined categories), unsupervised approaches (text clustering and topic extraction). The course includes applications and exercises with Knime Analytics and R.

Course leader

Francisco Villarroel Ordenes (University of Massachusetts Amherst, Isenberg School of Management)

Target group

PhD students and researchers of social sciences who want to apply text analysis in their fields.

Course aim

The course aims to provide a solid background and applicative competences on text mining techniques.

Fee info