Abstract
The pandemic period can change the habits of a person and organization, where all meetings are not held face-to-face/offline but virtually, so it is not uncommon for meetings to be attended by employees who are not Persons in Charge (PIC) on certain meeting topics. This study aims to identify trends in time, day, and duration of meetings within the Secretariat General of the Ministry of Finance and to cluster meeting matters into several themes so that further identification can be carried out to provide recommendations for units having duties related to the meeting using networking analysis. This study uses the Natural Language Processing (NLP) method with Latent Dirichlet Allocation (LDA) which can conclude the factors that represent topics to produce topic clustering and Social Network Analysis (SNA) modeling using the Degree Centrality method to find out the closest relationship between topics and names. unit based on the highest centrality value and the possibility of a unit attending a meeting that discusses a particular topic. Data used in this reseacrh are meetings held during April 2020 up to April 2022 with 59,891 data records. The modeling results shows clustering result dashboard based on meeting topics and to produce an analysis of which meeting topics are often discussed and become a concern. The results of the research are expected to be used to provide recommendations to unit leaders to assign meeting dispositions for each PIC to attend the meeting.
Published Version
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call