Analysis of Emoticon and Sarcasm Effect on Sentiment Analysis of Indonesian Language on Twitter

Sigit Priyanta,Debby Alita,Nur Rokhman

doi:10.20473/jisebi.5.2.100-109

Abstract

Background: Indonesia is an active Twitter user that is the largest ranked in the world. Tweets written by Twitter users vary, from tweets containing positive to negative responses. This agreement will be utilized by the parties concerned for evaluation.Objective: On public comments there are emoticons and sarcasm which have an influence on the process of sentiment analysis. Emoticons are considered to make it easier for someone to express their feelings but not a few are also other opinion researchers, namely by ignoring emoticons, the reason being that it can interfere with the sentiment analysis process, while sarcasm is considered to be produced from the results of the sarcasm sentiment analysis in it.Methods: The emoticon and no emoticon categories will be tested with the same testing data using classification method are Naïve Bayes Classifier and Support Vector Machine. Sarcasm data will be proposed using the Random Forest Classifier, Naïve Bayes Classifier and Support Vector Machine method.Results: The use of emoticon with sarcasm detection can increase the accuracy value in the sentiment analysis process using Naïve Bayes Classifier method.Conclusion: Based on the results, the amount of data greatly affects the value of accuracy. The use of emoticons is excellent in the sentiment analysis process. The detection of superior sarcasm only by using the Naïve Bayes Classifier method due to differences in the amount of sarcasm data and not sarcasm in the research process.Keywords: Emoticon, Naïve Bayes Classifier, Random Forest Classifier, Sarcasm, Support Vector Machine

Highlights

Twitter is a social media that can be used by all people to express themselves freely, so Twitter has a significant user increase [1]
The results of testing the Naïve Bayes Classifier method without the use of emoticons provide the highest accuracy value in testing 6-Fold cross validation and the precision, recall and F1score values are best done through 10-Fold cross validation with an accuracy of 52.91%, precision values of 50.32 %, 46.91% recall value and F1Score value 46.75%
The results of the sarcasm detection test with the Support Vector Machine method provide the best value of accuracy, precision, recall and F1score done through 7-Fold cross validation with an accuracy value of 61.13%, a precision value of 60.45%, a recall value of 62.69% and F1Score value of 58.80%

Summary

Introduction

Twitter is a social media that can be used by all people to express themselves freely, so Twitter has a significant user increase [1]. Tweets written by Twitter users vary, from tweets containing positive to negative responses. This agreement will be utilized by the parties concerned for evaluation. Emoticons are considered to make it easier for someone to express their feelings but not a few are other opinion researchers, namely by ignoring emoticons, the reason being that it can interfere with the sentiment analysis process, while sarcasm is considered to be produced from the results of the sarcasm sentiment analysis in it. Results: The use of emoticon with sarcasm detection can increase the accuracy value in the sentiment analysis process using Naïve Bayes Classifier method. The detection of superior sarcasm only by using the Naïve Bayes Classifier method due to differences in the amount of sarcasm data and not sarcasm in the research process

Objectives

Methods

Results

Discussion

Conclusion