Modulcode: | infTM-01a |
Englische Bezeichnung: | Text Mining |
Modulverantwortliche(r): | Prof. Dr. Ralf Krestel |
Turnus: | unregelmäßig (SS23 WS24/25 SS26) |
Präsenzzeiten: | 2V 2Ü |
ECTS: | 6 |
Workload: | 30 Std. Vorlesung, 30 Std. Präsenzübung, 150 Std. Selbststudium |
Dauer: | ein Semester |
Modulkategorien: | BSc-Inf-WP (BSc Inf (21)) BSc-WInf-WP-WInf (BSc WInf (21)) 2F-MEd-Inf-WP (MEd-Hdl Inf (21)) 2F-MA-Inf-WP (2F-MA Inf (21)) |
Lehrsprache: | Englisch |
Voraussetzungen: | infEInf-01a |
The digital age and the success of the Internet in particular has led to a huge amount of publicly available documents and textual information. The task of text mining is to process this unstructured information and extract knowledge. To this end, we will present methods, algorithms, and models that support a diverse set of text mining applications, ranging from regular expressions and lexicon-based sentiment analysis, to more complex methods using machine learning, such as probabilistic topic models.
Students are able to...
Foundation of linguistics Information extraction Named entities Opinion mining & sentiment analysis Preprocessing of textual data Representation of documents Word associations Topic Modeling Foundations of machine learning Document classification Clustering Sequence labeling Visualizing textual data Ethics & bias
Concepts are introduced in the lectures with the help of examples and specific application tasks. In the exercise the knowledge is deepened and applied - guided by weekly homework assignments.