Emotion Analysis for SMILE Twitter dataset.
Dataset is taken from the following resource:
Wang, Bo; Tsakalidis, Adam; Liakata, Maria; Zubiaga, Arkaitz; Procter, Rob; Jensen, Eric (2016): SMILE Twitter Emotion dataset. figshare. Dataset. https://doi.org/10.6084/m9.figshare.3187909.v2
- Google colab was used with GPU (Tesla T4) provided by Google as the runtime machine.
- Dataset contains following sentiment classes.
| Sentiment | Count |
|---|---|
| nocode | 1572 |
| happy | 1137 |
| not-relevant | 214 |
| angry | 57 |
| surprise | 35 |
| sad | 32 |
| happy/surprise | 11 |
| happy/sad | 9 |
| disgust/angry | 7 |
| disgust | 6 |
| sad/disgust | 2 |
| sad/angry | 2 |
| sad/disgust/angry | 1 |
- Sentiment/Emotion analysis with machine learning models Logistic Regression and Naive Bayes.
- Sentiment/Emotion analysis with BERT with classification head (BERTForSequenceClassification).
- Samples containing multi-label class and nocode class were removed in preprocessing.