Introduction to Computational Text Analysis for Historians - Detailseite

This course aims at providing an introduction to Computational Text Analysis for History scholars. The course is designed to provide the theoretical fundamentals of the discipline, supported by concrete examples and hands-on sessions. By using established off-the-shelf tools, the students will familiarize with a standard processing pipeline and with the principles of Text Analytics, as well as with basic Information Extraction techniques (with focus on Named-Entity Recognition). 

Prerequisites: a basic knowledge of the Python programming language (variables, datatypes, working with files, control flow) is very welcome, but not a requirement. A refresher about the mentioned programming topics will be given before the start of the course (approximately one week before, more information will be provided).

Outcome: as a result of attending the course, students should be able to instantiate a Text Analysis pipeline on a new text and automatically extract information from it, as well as to adapt the pipeline to their own purposes.

If you are interested in this class, please also write a message to marco.rovera@hu-berlin.de after 21 October. The class will be held in the end of February or at the beginning of March as Block class.

Ausgleichsberechtigte Studierende wenden sich zur bevorzugten Platzvergabe per E-Mail mit einem Nachweis der Ausgleichsberechtigung an die Studienkoordinationsstelle Geschichte. Ausschlussfrist für die Geltendmachung von Ausgleichsberechtigungen ist der letzte Tag der zentralen Frist, 16 Uhr. Textnachrichten in AGNES werden hingegen nicht gelesen!