Search

Current filters:

Current filters:

Author

Subject

Date issued

Has File(s)

Search Results

Results 1-1 of 1 (Search time: 0.001 seconds).
  • <<
  • 1
  • >>
    • Emotion classification of Indonesian Tweets using Bidirectional LSTM
    Authors: Aaron, Glenn; Phillip, LaCasse; Bruce, Cox;  Advisor: -;  Co-Author: - (2023)

    Emotion classification can be a powerful tool to derive narratives from social media data. Traditional machine learning models that perform emotion classification on Indonesian Twitter data exist but rely on closed-source features. Recurrent neural networks can meet or exceed the performance of state-of-the-art traditional machine learning techniques using exclusively open-source data and models. Specifically, these results show that recurrent neural network variants can produce more than an 8% gain in accuracy in comparison with logistic regression and SVM techniques and a 15% gain over random forest when using FastText embeddings.