Course 2024-2025 a.y.

Below there is a list of the topics covered in the course:

• Introduction to Natural Language Processing (NLP) and Machine Learning (ML) methods, their common forms and present-day business applications.
• Obtaining and preprocessing textual data.
• Representing textual data mathematically.
• Text classification.
• Extraction of valuable information from text.
• NLP applications in accounting, finance, law, and other practice areas and industries.
• Ethics in NLP.

After successful completion of this course, students will acquire knowledge of how to:

• Define key concepts of Natural Language Processing (NLP) and Machine Learning (ML).
• Describe the process of obtaining and preprocessing textual data, including web scraping and APIs.
• Identify common sources and types of textual data relevant for business applications.
• Recognize the role of feature extraction methods, such as vectorization and embeddings, in NLP tasks.
• Illustrate the value of information extraction techniques, including named entity recognition and sentiment analysis, for business decision-making.
• Summarize the applications of NLP and ML across different practice areas such as accounting, finance, and law.
• Distinguish between basic and advanced NLP models, such as traditional classifiers and transformers.

After successful completion of this course, students will be able to:  

• Apply core NLP and ML methods in various business environments and practice areas such as accounting, finance, etc.
• Discuss key theoretical concepts behind the methods.
• Develop web scrapers to extract textual data from websites with publicly available business information.
• Analyze textual data with the purpose of making business decisions.
• Justify the use of chosen NLP methods for specific business purposes.
• Apply machine learning models, evaluate the model performance, and interpret the output with the purpose of making business decisions.

• Lectures
• Practical Exercises
• Individual works / Assignments

Exercises: Writing Python code snippets, testing them using real-world data, and interpreting their outcomes.

Case studies: Most topics will be accompanied by brief case studies with code snippets that students can utilize in the future.

Individual assignments: An individual assignment (“take-home test”) will be a part of the grading scheme (please see below).

ATTENDING

For the first time student take the exam, the grade will be determined as the best between (A) a combination of your grade on one “take-home” test (with a weight of 25% of the total grade) plus the final exam (weight of 75%), and (B) 100% weight on the final exam.

For any retake, the grade will be entirely determined based on the final exam (i.e., its weight will be 100%).

The “take-home” test will be distributed and accessible via Blackboard.

The final exam is written, and based on the material discussed in class.

NOT ATTENDING

The grade will be entirely based on the final exam.

For a large part of the course, the course will use

Vajjala, S., Majumder, B., Gupta, A., & Surana, H. (2020). Practical natural language processing: a comprehensive guide to building real-world NLP systems. O'Reilly Media.

Other required textbooks and materials will be posted on Blackboard before the start of the course. Any required textbooks will be in the eBook format.