Clustering of Librarians' Initial Knowledge on the Theme of Training

Background of study: The implementation of librarian competency development through training in Sidenreng Rappang Regency, South Sulawesi Province, was carried out by dividing librarians based on the location of their agency's work area. In practice, there are training barriers, namely differences in absorption of the material due to limited training time and differences in initial knowledge of the training material. Purpose: According to the librarian's prior knowledge of the training to be held in future, this study attempts to determine the best grouping and number of participants. Method: The methodology used in this research is Cross Industry Standard Process for Data Mining (CRISP-DM) which consists of 6 stages. The data collection technique used a questionnaire with a linear numerical scale from a score of 0 to 10 to 97 librarians in Sidenreng Rappang Regency. Data were analyzed using the K-Means algorithm to determine the number of groups and the number of librarians in each group and evaluated using the Davies-Bouldin index (DBI) algorithm to determine the most optimal group division. Findings: According to this study, the best number of groups for training in the processing of library materials is two under a DBI value of 0.68983. With a DBI value of 0.69431, the best number of groups is two in the library promotion training. Conclusion: the library service training had the best number of groups of 2 with a DBI value of 0.65698. Meanwhile, for INLISLite-based automation training, the best number of groups is two groups with a DBI value of 0.65500.