• Dinar Ajeng Kristiyanti  STMIK Nusa Mandiri Jakarta


Sentiment  analysis  is  a  computational  study  of  the  opinions,  behaviors  and  emotions  of  people  toward  the entity. The entity describes the individuals, events or topics. That topics generally could be the review of diverse datasets, one of which is a product review. By reading the review of products based on the experiences of other consumers,  it  will  be  recognized  the  quality  of a  product.  It  goes  without  saying,  as  cosmetic products  on the market today are very diverse, both in terms of type and brand. However, not all cosmetics have good quality in line with the needs of consumers and it is to be noticed by the consumer. Lately consumers who are writing their opinions,  reviews  and  experiences  through  online  is  increasing.  So,  reexamination  of  the  cosmetic  product review by classifying these reviews into positive and negative class is an excellent way to determine the response of other consumers about the product quickly and accurately. Among of the techniques for classification mostly used by data classification is Support Vector Machine (SVM). SVM has the advantage of being able to identify the  separated  hyper  plane  that  maximizes  the  margin  between  two  different  classes.  However,  SVM  has  a weakness  for  parameter  selection  or  suitable  features.  Feature  selection  set  up  the  parameters  in  SVM  that significantly  affects  the  results  of  classification  accuracy.  Feature  selection  also  can  be  used  to  reduce  the attributes  that  are  less  relevant  to  the  dataset.  To  improve  the  previous  research,  this  research  uses  the combined method of feature selection in Algorithm Support Vector Machine by comparing two-feature selection, namely  Particle  Swarm  Optimization  and  Genetic  Algorithm.  It  is  in  order  to  improve  the  accuracy  of  the classification of Support Vector Machine. Furthermore the research found the text classification in a positive or negative format from the cosmetic products review. Measurement is based on Support Vector Machine accuracy before  and  after  adding  the  feature  selection  method.  The  evaluation  was  done  by  using  10  Fold  Cross Validation. While the accuracy measurement is done by using the Confusion Matrix and ROC Curve. The results of integrated Support Vector Machine Algorithm and Feature Selection Algorithm, Particle Swarm Optimization indicate the best results with average accuracy 97.00% and the average AUC 0.988. While Genetic Algorithm show the best results with average accuracy 94.00% and average of AUC 0.984. As conclusion, the research of Support  Vector  Machine  Algorithm  showed  the  best  accuracy  improvement  toward  the  integrated  feature selection Particle Swarm Optimization with the increased accuracy from 89.00% to 97.00%. 


Download data is not yet available.

Author Biography

Dinar Ajeng Kristiyanti , STMIK Nusa Mandiri Jakarta

Jl. Damai No.8, Warung Jati Barat (Margasatwa), Ragunan, Pasar Minggu, Jakarta Selatan 

How to Cite
KRISTIYANTI , Dinar Ajeng. ANALISIS SENTIMEN REVIEW PRODUK KOSMETIK MELALUI KOMPARASI FEATURE SELECTION. Konferensi Nasional Ilmu Pengetahuan dan Teknologi, [S.l.], v. 1, n. 1, p. 69-76, aug. 2015. Available at: <>. Date accessed: 29 sep. 2020.
Article Metrics

Abstract viewed = 146 times
PDF downloaded = 128 times