Although text mining has been successfully used in the educational sector for quite some time, its application in the field of structuring teaching materials is still unexplored regarding the learning objectives contained therein. Our intention was therefore to use text mining to develop an approach to derive statements about the current composition and structure of learning objectives in the field of "Data Science". For the extraction, pre-processing, transformation, classification, and visualization of these structures, different methods and techniques of text mining were applied and combined with the competence levels according to Bloom to form learning objectives. Thereby, the leading teaching topics in the field of "Data science" were identified and characteristics and specificity of the competence levels in a networked structure were presented as a knowledge graph. This provides both researchers and practitioners with valuable new insights into the potential of this new data collection using existing teaching material structures.
Trampler, Michael; Koch, Julian; Vollenberg, Carolin; and Coners, André, "Structure Mining: Deconstruction of Data Science From the Perspective of Teaching Literature" (2021). PACIS 2021 Proceedings. 236.
When commenting on articles, please be friendly, welcoming, respectful and abide by the AIS eLibrary Discussion Thread Code of Conduct posted here.