Leveraging Latent Dirichlet Allocation for Feature Extraction in User Comments: Enhancements to User-Centered Design in Indonesian Financial Technology

Abstract

The burgeoning Financial Technology (FinTech) sector in Indonesia, while witnessing a surge in user base, contends with limitations in system functionalities and service offerings. The extraction of latent features from user comments is imperative for the identification of these inadequacies, serving as a catalyst for innovation and delivering advantages to both consumers and developers of FinTech applications. This study employs Latent Dirichlet Allocation (LDA) algorithm, an intelligent probabilistic model, to discern and extract underlying topics within narratives found in user comments on FinTech platforms. In this approach, words within each topic are ranked according to their respective probabilities. Through the LDA algorithm, ten salient topics, each comprising ten keywords, have been identified. These topics coalesce into three broad categories: system improvements in applications, services that are out of sync with the system, and service satisfaction. The coherence of the topics has been quantitatively assessed, with an average score of 0.564, indicative of substantial coherence. Findings from the LDA model are integrated into the User-Centered Design (UCeD) framework, wherein the algorithm streamlines the UCeD's evaluative and abstraction processes, as well as the grouping of user necessities. This integration aids FinTech management teams in pinpointing pertinent user feedback, thereby facilitating the refinement of application development.