This course focuses on using pre-existing Natural Language Processing (NLP) tools and Large Language Models (LLMs) to transform vast amounts of unstructured text into actionable decisions. It draws on computational linguistics and machine learning methods developed to automate insights, test hypotheses, and evaluate textual data.

In particular, this course will provide a review of text preprocessing including regex, tokenization, and string normalization using R packages. In addition, the course will cover automated sentiment classification using VADER, unsupervised clustering (TF-IDF and K-Means), contextual embeddings with pre-trained BERT models, and LLM orchestration via prompt engineering, system personas, and context management.

On successful completion of the course, you should:

• understand how to transform unstructured text into structured, machine-ready data;
• be able to choose the right NLP or text-mining method to answer a research question;
• have a strong understanding of transformer architectures and Large Language Models;
• be able to present and discuss text-derived insights using automated reporting tools;
• perform end-to-end text analytics pipelines using statistical software (R).

Attendance is expected for more than 80% of lectures. If you cannot attend a session due to exceptional circumstances, please contact the lecturer.

The text mining course is centered on specific problem-based examples and hands-on coding. Each 3-hour session is divided into a 90-minute lecture covering theory and business use-cases, followed by a 90-minute collaborative hands-on coding session. In weekly homework assignments, students are asked to try out text analysis themselves, applying the concepts to new datasets provided to them.

• Weekly Homework Assignments (30%)
• Participation and Quizzes (20%)
• Final Evaluation / Hackathon (50%)

Basic familiarity with R and Python. The waiting list is open and active during the official registration period. The class is designed for a maximum of 15 students. 12 spots are up for grabs in LPIS, the remaining spots will be allocated by us. Your ranking on the waiting list does not matter, however we will try to acommodate everyone's wishes.

Please log in with your WU account to use all functionalities of read!t. For off-campus access to our licensed electronic resources, remember to activate your VPN connection connection. In case you encounter any technical problems or have questions regarding read!t, please feel free to contact the library at readinglists@wu.ac.at.