Paper Number
1235
Paper Type
Complete Research Paper
Abstract
Scientometric studies play a crucial role in revealing trends in scientific research. The IS discipline also has a rich history of using scientometric studies to understand its own development. However, conducting scientometric studies and identifying trends is often hampered by the time-consuming and labor-intensive manual classification of large volumes of research papers. To overcome these challenges, we take a design science approach and propose the development of a text classification-based assistance system that can support IS scholars in classifying the relevance, research paradigms, and research methods of research papers. Leveraging design science research, we designed and developed an intelligent assistance system that incorporates supervised learning text classification models and demonstrates high performance and robustness while providing a convenient user experience. Thus, the prototype not only addresses the existing challenges of scientometric studies but also lays the foundation for further improvements by simplifying scientometric studies through the integration of text classification.
Recommended Citation
Schmidt, Jan-Hendrik; Goutier, Marc; Koch, Ludwig; Schwinghammer, Ronja; and Benlian, Alexander, "Automatic Classification of IS Research Papers: A Design Science Approach" (2024). ECIS 2024 Proceedings. 8.
https://aisel.aisnet.org/ecis2024/track02_general/track02_general/8
Automatic Classification of IS Research Papers: A Design Science Approach
Scientometric studies play a crucial role in revealing trends in scientific research. The IS discipline also has a rich history of using scientometric studies to understand its own development. However, conducting scientometric studies and identifying trends is often hampered by the time-consuming and labor-intensive manual classification of large volumes of research papers. To overcome these challenges, we take a design science approach and propose the development of a text classification-based assistance system that can support IS scholars in classifying the relevance, research paradigms, and research methods of research papers. Leveraging design science research, we designed and developed an intelligent assistance system that incorporates supervised learning text classification models and demonstrates high performance and robustness while providing a convenient user experience. Thus, the prototype not only addresses the existing challenges of scientometric studies but also lays the foundation for further improvements by simplifying scientometric studies through the integration of text classification.
When commenting on articles, please be friendly, welcoming, respectful and abide by the AIS eLibrary Discussion Thread Code of Conduct posted here.