Search
Author
- Aaron, Glenn (1)
- Bruce, Cox (1)
- Phillip, LaCasse (1)
Date issued
- 2023 (1)
Has File(s)
- true (1)
Search Results
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. |