Modul

PDF-Export
Allgemeine Informationen
Social Media Analytics
Social Media Analytics
MADS-SMA
SocialMedAna-01-MA-M
Prof. Dr. Schwörer, Tillmann (tillmann.schwoerer@haw-kiel.de)
Prof. Dr. Schwörer, Tillmann (tillmann.schwoerer@haw-kiel.de)
Wintersemester 2024/25
1 Semester
In der Regel jedes Semester
Englisch
Studiengänge und Art des Moduls (gemäß Prüfungsordnung)
Studiengang Vertiefungsrichtung Schwerpunkt Modulart Fachsemester
M.Sc. - DS - Data Science Pflichtmodul
Kompetenzen / Lernergebnisse
Kompetenzbereiche: Wissen und Verstehen; Einsatz, Anwendung und Erzeugung von Wissen; Kommunikation und Kooperation; Wissenschaftliches Selbstverständnis/Professionalität.
Students
- know the fundamentals of social media analytics
- know the most commonly used concepts and techniques in the field of natural language processing and network analysis
Students
- are able to apply state-of-the art algorithms in the field of NLP and network analysis to solve real-word problems
- are able to evaluate the usefulness and quality of algorithms and results
- are able to critically assess the social implications of algorithms and applications
Students
- are able to report and present solutions for practical project tasks
- are able to leverage the individual skills of all team members
Students
- are able to work professionally in the field of social media analytics
- are able to give and accept professional feedback to different topics of social media analytics
- are able to identify and process relevant scientific literature
Angaben zum Inhalt
Course contents:

1. Handling Social Media Data
1.1 Data Acquistion: APIs and Web Scraping
1.2 Data Storage: JSON, Document databases, vector stores

2. Social Network Analysis
2.1 Network analysis and visualization

3. Natural Language Processing (NLP)
3.1 Classical NLP
3.1.1 Preprocessing and feature engineering for text data
3.1.2 Training supervised and unsupervised machine learning models for text data
3.1.3 Topic Modelling

3.2 Transformers in NLP
3.2.1 Embeddings
3.2.2 Transformers and Large Language Models
3.2.3 Transfer learning with Encoders
3.2.4 Generative Language Models
3.2.5 Retrieval Augmented Generation

Example Applications:
- Text classification: e.g. Sentiment Prediction, Hate Speech Detection
- Token classification: e.g. Named Entity Recognition
- Information extraction and text summarization
- Lecture Slides
- Jurafsky, D. and Martin, J.H. (2024): Speech and Language Processing. An Introduction to Natural Language Processing, Computational Linguistics, and Speech Recognition, available online: https://web.stanford.edu/~jurafsky/slp3/ed3bookfeb3_2024.pdf
- Sarkar, D. (2019): Text Analytics with Python
Lehrformen der Lehrveranstaltungen
Lehrform SWS
Lehrvortrag + Übung 4
Arbeitsaufwand
4 SWS
5,0 Leistungspunkte
48 Stunden
102 Stunden
Modulprüfung
Prüfungsform Dauer Gewichtung wird angerechnet gem. § 11 Absatz 2 PVO Benotet Anmerkung
Portfolioprüfung 100 %
Sonstiges
Solid knowledge of Python Programming and Machine Learning
PDF-Export