Sentiment Analysis of Negative Comments on Social Media Using Long Short-Term Memory (LSTM) Method With TensorFlow Framework

  • Iwan Giri Waluyo
  • Juwono
N/ACitations
Citations of this article
8Readers
Mendeley users who have this article in their library.

Abstract

There are still many unidentified negative comments on social media that have a negative impact on others' mental and physical well-being. Therefore, sentiment analysis is needed to filter and identify such types of comments, especially on social media. This research aims to analyze and classify unidentified negative comments spread across social media. Sentiment analysis and comment classification are performed using 7773 comments in the Indonesian language. The comments are then visualized using an embedding projector, which gives satisfactory results in classifying words in the comments, where words with negative or positive sentiments are clustered closely together. The model employed in this study is the Long Short Term Memory (LSTM) model, which achieved an accuracy rate of 77.70% and a validation accuracy of 85.20%. The trained model is then used for testing purposes, employing directly collected comments from social media, which give satisfactory results

Cite

CITATION STYLE

APA

Iwan Giri Waluyo, & Juwono. (2023). Sentiment Analysis of Negative Comments on Social Media Using Long Short-Term Memory (LSTM) Method With TensorFlow Framework. International Journal of Integrative Sciences, 2(7), 1015–1030. https://doi.org/10.55927/ijis.v2i7.4990

Register to see more suggestions

Mendeley helps you to discover research relevant for your work.

Already have an account?

Save time finding and organizing research with Mendeley

Sign up for free