Interpreting Information in Text by Humans and Machines

COURSE OBJECTIVE
In this course, students are trained in systematic text analysis. In particular, we explore the process of identifying and annotating information in historic and contemporaneous texts such as novels, lyrics, letters, newspaper articles, movie scripts, blogs and other social media texts using manual and automatic methods.

By the end of the course :
* students are able to formulate a humanities or social analytics research question that can be answered by the information found in a (set of) texts of their choice and identify this information in the text.
* students are able to make the relevant information explicit by carrying out a linguistic annotations task. They know how to perform this task following methods for annotation schema design, and inter-annotator agreement calculations and using annotation tools (CAT).
* students are able to build and apply basic text mining techniques (in particular sentiment and emotion analysis) to find the relevant information automatically.
* students are able to reflect on the results of the automatic analysis by performing a qualitative and quantitative error analysis.
* students are able to present their findings in a research paper.

COURSE CONTENT
This module addresses the process of systematic text analysis through (1) human annotation and (2) automatic analysis using text mining
techniques. Annotations make information that is implicit in data explicit, allowing researchers to explore their data, identify patterns and answer various research questions in a methodologically sound way. It also requires the use of some type of interpretation model and it results in an analysis that can be compared across annotators. The degree to which annotators agree or disagree (the so-called Inter Annotator Agreement) tells us something about the reproducibility of the interpretation process, the matureness of theoretical notions and the criteria used to apply them to real data. Text mining techniques can be used to automatically find the same or similar information in text. Some of these techniques are off the shelf software, but most of them need to be built or fine-tuned to carry out a specific task. How do these techniques work? Can a machine do better than humans? Is it possible to use the automatic annotations to extract useful informations from the text and to answer research questions?

TEACHING METHODS
Lectures, seminars

TYPE OF ASSESSMENT
Weekly assignments and a final research paper.

ENTRY REQUIREMENTS
Python (basics)