COMPARATIVE ANALYSIS OF ONLINE REVIEW PLATFORMS: IMPLICATION IN ELECTRONIC SERVICE QUALITY FOR VIDEO PLAYERS AND EDITOR APPS (YOUTUBE AND TIKTOK)
This study uses sentiment analysis, topic modeling, pearson correlation, and linear regression to identify the critical improvements that video-sharing platforms, particularly YouTube and TikTok, should make in the future to better handle user reviews. Given that video sharing provides viewers with an extremely immersive and engaging experience, its growing significance in relation to user feedback is becoming progressively apparent for companies. We initially preprocess 21,365 user reviews using Naïve Bayes classification, and we divide them into seven groups according to the dimensions of e-service quality: efficiency, responsiveness, system availability, compensation, fulfillment, contact, and privacy. The accuracy percentages for TikTok and YouTube came out as 80.33% and 75.56%, accordingly, indicating excellent performance in evaluating the quality of both platforms. Sentiment analysis revealed a higher prevalence of negative sentiment on TikTok and YouTube. Then, topic modeling based on Latent Dirichlet Allocation (LDA) evaluates the sentiment of the topic as well as the model of the topics discussed. The purpose of this research is to help both companies and individuals map public opinion toward a certain topic by analyzing the sentiment of the text and creating a topic model. We also measure the relationship between service quality using user sentiment and ratings, then predict future user ratings using predictive analysis methods such as linear regression. Regarding the classification of dimensions, we effectively draw attention to three dimensions— efficiency, fulfillment, and system availability —that are deemed important in the comparison between YouTube and TikTok. Then, the positive and significant relationship between service quality using user sentiment and ratings.
Sentiment Analysis, Topic Modelling, Regression Linear, Correlation, Service Quality, Media Sharing Network.