| Autor: |
Hakam W. Alomari, James D. Kiper, Vijayalakshmi Ramasamy, Urvashi Desai |
| Rok vydání: |
2018 |
| Předmět: |
|
| Zdroj: |
2018 IEEE International Conference on System, Computation, Automation and Networking (ICSCA). |
| DOI: |
10.1109/icscan.2018.8541228 |
| Popis: |
Clustering similar entities in relational tables is an open challenge to the research community due to the representation of transactional data as tables where the relationships between two or more entities are difficult to represent. This paper uses a graph-based modeling approach called Transaction Pattern Graph Miner (TP-GraphMiner) to identify clusters based on the similarities of the attributes in the transactions. It explores a socio-centric analysis that aims at educational decision-making processes such as identifying the relative engagement of female and male students in the coursework, the similarities of their interaction patterns, similar clusters of entities base on the attributes in the transactions, and the outliers - the entities with divergent interests. The empirical results of this initial investigation have revealed the following: while the rate of enrollment of female students in STEM courses is much lower than that of male students, the clustering results reveals greater active participation of the female students in computer programming courses and their prominent engagement in knowledge sharing and answering their peers’ questions. |
| Databáze: |
OpenAIRE |
| Externí odkaz: |
|
