Title: Identification of user satisfaction dimensions in open data services system using latent Dirichlet allocation: a case study of BMKG online data

Authors: Abdullah Hasan; Achmad Nizar Hidayanto; Ryan Randy Suryono

Addresses: Faculty of Engineering and Computer Science, Universitas Indonesia, Indonesia ' Faculty of Engineering and Computer Science, Universitas Indonesia, Indonesia ' Faculty of Engineering and Computer Science, Universitas Indonesia, Indonesia

Abstract: The Meteorology, Climatology, and Geophysics Agency (BMKG) presents a government open data portal that contains daily climate information and is freely accessible to users. Within this portal, there is a feature to provide feedback as an assessment of the services provided by BMKG's online data. Analysis of this feedback data is considered crucial in response to the decrease in the public satisfaction index (IKM) by 2.81 points. The aim of this study is to identify the topics that constitute the dimensions of user satisfaction with BMKG's online data. Previously, research had been conducted that involved the identification of topics within a company using the latent Dirichlet allocation (LDA) method. By applying the LDA model to user feedback data in text form, we successfully identified four dimensions related to satisfaction in using the BMKG data portal.

Keywords: user satisfaction; open government data; OGD; user reviews; topic modelling; latent Dirichlet allocation; LDA.

DOI: 10.1504/EG.2025.145912

Electronic Government, an International Journal, 2025 Vol.21 No.3, pp.279 - 299

Received: 04 Dec 2023
Accepted: 11 Apr 2024
Published online: 30 Apr 2025 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article