Explore our knowledge

MSc in Business Administration and Data Science

Nat­ur­al Lan­guage Pro­cessing and Text Ana­lyt­ics

About the course

Subjects
Statistics Quantitative methods IT

Course content

The course provides knowledge of various concepts, techniques, and methods related to text analytics. Furthermore, it introduces

  • Basics of Natural Language Processing (NLP) such as POS-tagging, Named-Entity recognition
  • Language Modeling using N-grams
  • Text classification such as Naïve Bayes and Logistic Regression
  • Lexicon Based Sentiment Analysis
  • Unsupervised methods for NLP and latent models.
  • Word-embeddings and Word Vectors
  • Neural Networks for NLP and Neural Language Models
  • Semantic textual similarity
  • Word-sense disambiguation
  • Text summarization
  • Deep Learning Models for NLP

Furthermore, the course provides the students with practical hands-on experience on text analytics using open source machine learning libraries such as scikit-learn, Natural Language Toolkit (NLTK), spacy, Gensim in Python programming language. After completing the course the students will be able to apply and use various NLP techniques such as text classification, sentiment analysis,  topic modelling etc. on textual documents/ text corpora.

See course description in course catalogue

What you will learn

To achieve the grade 12, students should meet the following learning objectives with no or only minor mistakes or errors:

  • Characterize the phenomena of text analytics and Natural Language Processing
  • Summarize different fundamental concepts, techniques and methods of Natural Language Processing
  • Analyze and apply different text analytics techniques for big/business datasets in organizational contexts
  • Understand the linkages between business intelligence and text analytics and the potential benefits for organizations
  • Summarize the application areas, trends, and challenges in text analysis
  • Exhibit deeper knowledge and understanding of the topics as part of the project and the report should reflect on critical awareness of the methodological choices with written skills to accepted academic standards

Course prerequisites

This course requires a fundamental understanding of programming in Python language as achieved in, or comparable to "Foundations of Data Science: Programming and Linear Algebra" at 1st semester CM (data science). Additionally, having a fundamental understanding of probability concepts such as independent assumption, conditional probability, Bayes' theorem, Chain rule, Markov Assumption, etc. would be advantageous.

Facts

Level
Master
Type
Mandatory course – also offered as elective
ECTS
7.5
Code
CD­SCO1002U
Teaching periods
Spring – semester
Academic year
2024/2025
Status
Available places
Teaching language
English
Teaching Format
Hybrid
Exams
  • Written assignment and oral exam on campus
    Group exam, summer
Assessment type
  • 7 point grading scale