<![CDATA[In the midst of rapid technological developments, the internet has changed people’s lifestyles, such as in terms of shopping. When shopping via the internet, one thing that needs to be considered is customer reviews. The problem arises when the number of existing customer reviews is very large, so the amount of information available is too much. To solve this problem, some online shopping platforms rank customer reviews from most helpful to least helpful. However, this system has several drawbacks, one of which is that it can be manipulated. So another way is needed to determine whether a review can help a potential customer decide to purchase a product. This study aims to create a review ranking model based on the review helpfulness from the regression review results. The method used in this study is the Random Forest Regression. There are six primary stages in this methodology, starting from collecting customer review data, preprocessing data, extracting aspects and analyzing aspect sentiment to determine the polarity of aspects, creating regression models and ranking, and analyzing the results. The results showed that the ranking model made based on the regression results had a superior performance compared to the model made based on the value of the helpfulness ratio alone. This is evidenced by the model being superior in testing the matching score which was carried out with an increase in performance of 6%.]]>
Copyrights © 2021
