Optimized support vector machine for sentiment analysis of game reviews

Abstract

The rapid development of games has made game categories diverse, so there are many opinions about games that have been released. Sentiment analysis on game reviews is needed to attract potential players. Sentiment analysis is carried  out  using  the  support  vector  machine  (SVM)  and  particle  swarm optimization  (PSO)  algorithms. SVMtraining  was  conducted  with  a  linear kernel,  the ‘C’value  parameter  was  10  resulting  in  an  accuracy  value  of 97.28%. The SVM algorithm optimized using the PSOmethod produces an accuracy  of  97.61%  using  the  parameters  c1  is  0.2,  c2  is  0.5  and  w  is  0.6. Based   on   these   results,   sentiment   analysis   using   PSO-based   SVM optimization  has been successfully  carried  out  with an  increase  in accuracy of 0.33%. This game review has a sentiment value from  neutral to positive so this game can be recommended to other players.