Lecture Data Modeling and Knowledge Generation
The Lecture Data Modeling and Knowledge Generation is part of the supplementary programme Data Literacy!
Data models represent the real world in the analysis process, they act as their placeholder, so to speak. As such, they create their own reality for the analyses. The formulation of data models is always subject to conscious and unconscious selection and transformation decisions. These decisions implicitly influence the way algorithms and analysts understand and process the real world.
At the same time, data models act as blueprints for a real world that comes after analysis. Finally, analysis results are produced and evaluated with the help of data models and communicated as new knowledge. The decisions mentioned above therefore have far-reaching implications for the expected results and the knowledge that can be gained from these results.
This dual role of description and prescription opens up a field of tension for the analysis process in interdisciplinary research as well as in numerous business areas that make use of "data driven decision making", for example.
Only when the data model, algorithm and results are viewed as a holistic unit of an analysis process can reliable knowledge be gained from data.
In this course, different methods for data analysis and knowledge generation will be presented - including methods from the fields of machine learning, data mining, text mining, social network analysis and information visualization. These methods, which are currently widely used in science, business and beyond, bring about different requirements for the modelling of data. These requirements are viewed critically. The implications for the expected results and the knowledge derived from them are explicitly stated.
Previous Knowledge Expected
Interest in computer-aided data analysis; no hesitation to participate in "active learning"; interest in a critical perspective on data analysis
Objective
Students will learn different methods for data analysis and knowledge generation - including methods from the fields of machine learning, data mining, text mining, social network analysis and information visualization.
Students become aware of the requirements for the required data models that the different analysis methods entail.
Students know how to critically question data analyses, how to specify the implicit modelling decisions and how to evaluate analysis results always against the background of these decisions.
Further Information
Slides, material, and further details can be found on https://mircoschoenfeld.de/lecture-data-modeling-and-knowledge-generation.html