Analyzing User Feedback on a Fan Community Platform - Weverse: A Text Mining Approach

Aug 29, 2026

The study investigates user experience and app problems voiced in English online reviews for the fan community platform Weverse on the Google Play Store. A dataset of 88,068 first-level reviews is collected with Google-Play-Scraper, then preprocessed to 31,861 reviews for analysis. Latent Dirichlet Allocation (LDA) topic modeling using the Gensim library in Python identifies five major topics, including network connection errors, delayed notifications, and incorrect translations. Results also highlight Weverse’s role in supporting fan-artist interaction and fan-to-fan relationships, enabling improved engagement and loyalty.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages10

Reading Time25 min

AccessFree to download

Abstract

Introduction

Related Work

Fan community platform

62 2024년 6월 스마트미디어저널 Smart Medhttpias:J/urdxaol i/oVorg/l1.1033,N06. 63//SISMSJN20:22248173-.1632622 |
Analyzing User Feedback on a Fan Community Platform
'Weverse': A Text Mining Approach
Thi Thao Van Ho, Mi Jin Noh, Yu Na Lee, Yang Sok Kim | | | --- | --- | | Abstract | | | This study applies topic modeling to uncover user experience and app issues expressed in users'online reviews of a fan community platform, Weverse on Google Play Store. It allows us to identify the features which need to be improved to enhance user experience or need to be maintained and leveraged to attract more users. Therefore, we collect 88,068 first-level English online reviews of Weverse on Google Play Store with Google-Play-Scraper tool. After the initial preprocessing step, a dataset of 31,861 online reviews is analyzed using Latent Dirichlet Allocation (LDA) topic modeling with Gensim library in Python. There are 5 topics explored in this study which highlight significant issues such as network connection error, delayed notification, and incorrect translation. Besides, the result revealed the app's effectiveness in fostering not only interaction between fans and artists but also fans' mutual relationships. Consequently, the business can strengthen user engagement and loyalty by addressing the identified drawbacks and leveraging the platform for user communication.
Keywords: Weverse| Topic modeling| LDA| Fan community platform| Communication | | | I. INTRODUCTION | Weverse is a global fan community platform, developed by Weverse Company | | Korean dramas and music have been | (formerly beNX) which is a subsidiary of | | gaining popularity in Asia for over a | HYBE Entertainment Company. It was | | decade. Further, the Korean wave, known | launched on June 10, 2019 , and later in | | as 'Hallyu' has now spread to Europe, | March 2022 acquired V Live which is also | | America, and other countries [1] . It cannot | a fan community platform run by Naver | | be denied that the globalization of Korean | corporation [3,4] . | | entertainment industry results in the | This application offers various functions | | increased demand to keep in touch with | to promote engagement between fans and | | idols. Moreover, artists' efforts to engage | artists such as direct messaging, exclusive | | actively with fans also contribute to the | livestream, and online concerts. Besides, it | | fast growth of this industry [2] . In the | allows users to send fan letters and get | | context of Hallyu and technological | access to official content and events [5] . | | development, fan community platforms or | Weverse emerged as the most popular | | fandom platforms were created to | and widely used fan community application, | | facilitate the communication between fans | with 100 million downloads by June 2023 | | and idols. | and over 120 artists joining this platform | Manuscript : 2024.05.03 Revised : 2024.06.03 Confirmation of Publication: 2024.06.10 Corresponding Author : Mi Jin Noh , e-mail : [mjnoh@kmu.ac.kr](mjnoh@kmu.ac.kr) Smart Media Journal / Vol.13, No.6 / ISSN:2287-1322 2024년 6월 스마트미디어저널 63 [3,6] . Consequently, we decided to conduct a study on user feedback on this application. The purpose of this research is to explore user experience and app issues by collecting user reviews of Weverse on Google Play Store with Google-PlayScraper tool and then analyzing them by utilizing Latent Dirichlet Allocation (LDA), a common topic modeling technique to reveal hidden topics in a corpus. LDA results and visualization are explained to understand the extracted topics. This helps to identify which aspects need to be improved and maintained to enhance user experience as well as accelerate app performance and attract new users. II. RELATED WORK 1. Fan community platform Fandom is defined as a group of enthusiastic fans of someone or something [7] . According to the research by Kim and Kim, a fan community platform or fandom platform i

FAQs

How is the user feedback data collected and prepared for analysis?

User reviews for Weverse on the Google Play Store are collected using the Google-Play-Scraper tool and then preprocessed to form a dataset of 31,861 reviews.

Which topic modeling method is used to uncover hidden themes in the reviews?

Latent Dirichlet Allocation (LDA) topic modeling is applied using the Gensim library in Python to discover and explain key topics.

What types of app issues are highlighted by the extracted topics?

The results emphasize significant problems such as network connection errors, delayed notifications, and incorrect translations.

Aug 29, 2026

Upload by Oliver Hayes