Syllabus
GRA 4164 Text as Data · 6 ECTS · MSc in Data Science for Business · BI Norwegian Business School · Fall 2026
Course responsible: Leif Anders Thorsrud (Department of Economics) and Vegard H. Larsen (Department of Data Science and Analytics).
About the course
Curious about how ChatGPT and other large language models actually work? This course brings you one step closer to that understanding by introducing natural language processing (NLP) applied in a business setting.
In today’s data-rich world, traditional tabular data is far outweighed by the information embedded in textual sources: newspaper articles, social media posts, customer reviews, books, and financial reports. To extract business relevant information from text we need to turn something high-dimensional and unstructured into something useful for quantitative analysis — that is NLP.
The course blends theoretical concepts with hands-on practical exercises. Themes include sentiment analysis, topic modelling, classification, and trend analysis. Prior exposure to programming, statistics, and machine learning is an advantage but not a requirement.
Learning outcomes
Knowledge
By the end of the course, the student will:
- Have a solid understanding of how NLP can be strategically integrated into business processes, leading to improved efficiencies and competitive advantages.
- Be able to discuss and differentiate between different NLP methodologies, and identify their strengths and weaknesses in relation to different business cases.
Skills
By the end of the course, the student will:
- Be proficient in selecting and applying relevant NLP tools and algorithms.
- Have the ability to create empirical models using text as data and apply them strategically to drive business growth, foster innovation, and gain a competitive edge in the digital era.
General competence
By the end of the course, the student will:
- Have a broader understanding of how different data sources can be used to create business value.
- Have hands-on and practical training in executing different NLP pipelines in a business case setting.
Course content
- Introduction to natural language processing: historical context, key milestones, business case examples, and data sources
- Text preprocessing: cleaning and preparing textual data; normalization, stemming, and lemmatization
- Supervised methods: Boolean/dictionary-based approaches and regression/classification on text
- Unsupervised methods: topic models and embeddings
- AI and large language models: tokenization, transformers, training and fine-tuning, prompt engineering
- Building NLP pipelines for business scenarios, case studies, and real-world applications
Assessment
| Component | Weight | Form |
|---|---|---|
| Submission | 30% | Group work (1–3 students): the four assignments collected into one submission at the end of the semester |
| School exam | 70% | Individual written exam, 3 hours, pen and paper |
Both components are graded on the ECTS scale. During the semester, groups present and receive feedback on each assignment. Permitted support materials for the school exam: BI-approved exam calculator, simple calculator, and a bilingual dictionary.
Workload
| Activity | Hours |
|---|---|
| Teaching | 24 |
| Seminar groups | 12 |
| Group work / assignments | 60 |
| Own work with learning resources | 64 |
| Total | 160 |
Prerequisites
Students will benefit from knowing some programming (Python), but it is not mandatory. Likewise, courses in mathematics and statistics, and knowledge of linear algebra, are an advantage.