Indonesian Social Media Sentiment Analysis With Sarcasm Detection

TL;DR

This paper addresses sarcasm detection in Indonesian social media sentiment analysis by introducing new features and employing machine learning, improving the accuracy of sentiment classification.

Contribution

The study proposes two novel features for sarcasm detection and utilizes translated SentiWordNet with machine learning for enhanced sentiment analysis.

Findings

Additional features improve sarcasm detection accuracy

Translated SentiWordNet enhances sentiment classification

Machine learning effectively integrates features for better results

Abstract

Sarcasm is considered one of the most difficult problem in sentiment analysis. In our ob-servation on Indonesian social media, for cer-tain topics, people tend to criticize something using sarcasm. Here, we proposed two additional features to detect sarcasm after a common sentiment analysis is conducted. The features are the negativity information and the number of interjection words. We also employed translated SentiWordNet in the sentiment classification. All the classifications were conducted with machine learning algorithms. The experimental results showed that the additional features are quite effective in the sarcasm detection.