| Approach Overview | Sentiment lexicon features, indicating how many positive or negative words are included in the tweet according to a predefined lexicon. |
| Experiments | Features Accuracy (%) Content features 61.1 + Sentiment lexicon features 63.8 + Target-dependent features 68.2 Re-implementation of (Bar- 60.3 bosa and Feng, 2010) |
| Experiments | Adding sentiment lexicon features improves the accuracy to 63.8%. |
| Experiments | Features Accuracy (%) Content features 78.8 + Sentiment lexicon features 84.2 + Target-dependent features 85.6 Re-implementation of (Bar- 83.9 bosa and Feng, 2010) |
| Introduction | The previously proposed J ST model uses the sentiment prior information in the Gibbs sampling inference step that a sentiment label will only be sampled if the current word token has no prior sentiment as defined in a sentiment lexicon . |
| Joint Sentiment-Topic (J ST) Model | For each word 21) E {1, ..., V}, if w is found in the sentiment lexicon , for each I E {1, ..., S}, the element Alw is updated as follows |
| Joint Sentiment-Topic (J ST) Model | where the function 8 returns the prior sentiment label of w in a sentiment lexicon , i.e. |
| Joint Sentiment-Topic (J ST) Model | The MPQA subjectivity lexicon is used as a sentiment lexicon in our experiments. |