Table 1 The evaluation results of smiley-labeled general, hand-labeled general, and hand-labeled domain-specific sentiment models on the test dataset in terms of the macro-averaged error rate and the macro-averaged F-score of positive and negative classes
From: Sentiment leaning of influential communities in social networks
Sentiment model | M error rate (%) | F avg |
|---|---|---|
Smiley-labeled general | 61.3 | 0.20 |
Hand-labeled general | 59.3 | 0.25 |
Hand-labeled domain-specific | 52.9 | 0.39 |