Diese Website verwendet nur technisch notwendige Cookies. In der Datenschutzerklärung können Sie mehr dazu erfahren.

Zum Hauptinhalt springen
Logo, Startseite der Hochschule der Medien
Veranstaltungsbeschreibung

335103b Big Data Projekt

Zuletzt geändert:06.07.2023 / Meth
EDV-Nr:335103b
Studiengänge: Studienübergreifendes Angebot - Minors, Prüfungsleistung im Modul Big Data Scenarios in Semester 1
Häufigkeit: nur WS
Wirtschaftsinformatik und digitale Medien (Bachelor, 7 Semester) , Prüfungsleistung im Modul Big Data Scenarios in Semester 7
Häufigkeit: nur WS
Dozent:
Sprache: Englisch
Art: P
Umfang: 2 SWS
ECTS-Punkte: 6
Workload: 45 hours teaching time + project work, preparation and follow-up work: 185 hours + exam preparation: approx. 70 hours = 300 hours
Inhaltliche Verbindung zu anderen Lehrveranstaltungen im Modul: This course is part of a module. The second course belonging to this module is 335103a Big Data Scenarios - Lecture
Prüfungsform:
Bemerkung zur Veranstaltung: Englisch
Beschreibung: The module “Big Data Scenarios“ introduces students to the analysis of large volumes of text data in different formats (structured, semi-structured, unstructured). The module consists of four elements: • The lecture introduces Big Data architectures, methods and concepts. To get an in-depth understanding of the introduced methods, they are applied in two types of labs: • tool-based labs, using state-of-the-art data science software (RapidMiner) and • method-based labs without any specific data science tool support. • Finally, students work in teams to implement a full big data analytics solution, applying the methods and tools, which they got to know in the labs. The module has no formal pre-requisites, but is addressed to bachelor students in their final semesters. No programming is required but good analytic skills, a high motivation and an interest to develop models.
English Title: Big Data Scenarios
English Abstract: The module “Big Data Scenarios“ introduces students to the analysis of unstructured text data. The module consists of three elements: • lecture: introduces Big Data architectures, methods and concepts. • technology-based labs, using state-of-the-art data science tools or programming languages • a project to apply everything learned in a broader context The module is addressed to bachelor students in their final semesters. Good analytic and programming skills, a high motivation and an interest to develop models are required.
Literatur: Manning, Christopher D., and Hinrich Schütze. Foundations of statistical natural language processing. MIT press, 1999. D. Jurafsky, J. H. Martin. Speech and Language Processing: An Introduction to Natural Language Processing, Speech Recognition, and Computational Linguistics (2nd ed.), Prentice-Hall, 2009.

Weitere Literatur finden Sie in der HdM-Bibliothek.