<![CDATA[PT ABC is one of the companies that provide online ticket-purchasing facilities amidst the rise of the digitalization era. So, companies need to see how application users complain as a form of evaluation and improvement. The rating results given by application users show a score of 3.3 from 172,000 reviews. The review results that will be examined are user reviews from January 2022 to April 1, 2023, which is more or less the last year of user comments. This research aims to form a review group using K-Means Clustering, the Elbow method, TF-IDF weighting, and analysis of review improvement strategies. The Elbow method is used to determine the optimal number of clusters so as not just to use assumptions. The success of the Elbow method in processing categorical data can be supported by assigning weights based on word frequency sequences using TF-IDF. The research analysis results show the formation of 4 clusters, with two tending to have negative sentiment, one neutral sentiment, and one positive sentiment. Mapping is carried out on each cluster to find out the characteristics of each cluster and possible causes of reviews, as well as providing solutions and strategies as a form of improvement. The problem of negative reviews appearing in each review group is different. It can be corrected with the proposed strategies, such as improving the appearance of features at the registration, ordering, and payment stages, adding payment methods, and carrying out regular system maintenance.]]>
Copyrights © 2023
