<![CDATA[Consumers who have shopped at E-Commerce will provide reviews/comments on products that have been purchased. Customer confidence in the rating is hampered due to inconsistency of answers such as reviews that have negative text with a positive rating value. For this reason, a technique is needed to adjust the rating with comments or reviews of purchased goods to make it easier for consumers when shopping to see the rating directly without reading the reviews/comments of previous buyers. purpose of this study is to classify comments and ratings and then obtain the results of the accuracy of the classification system so that the above problems can be answered.This study uses Support Vector Machine classification technique because this algorithm is better in classification’s terms. Data used are 1044 comment data and 1044 rating. Data are grouped into Good, Neutral, Less good categories using Python by Google Colab and divided into training and test data. To test capability of system, data that has been classified then analyzed using Confusion matrix. Results showed that SVM Algorithm was able to classify with an accuracy rate of 71.14%, 88% precision, and 79% recall.SVM algorithm is able to formulate training data with an accuracy of 91.3%.]]>
Copyrights © 2022
