Reserved Self-training: A Semi-supervised Sentiment Classification Method for Chinese Microblogs

The imbalanced sentiment distribution of microblogs induces bad performance of binary classifiers on the minority class. To address this problem, we present a semisupervised method for sentiment classification of Chinese microblogs. This method is similar to self-training, except that, a set of labeled samples is reserved for a confidence scores computing process through which samples that are less than a predefined confidence score threshold are incorporated into training set for retraining. By doing this, the classifier is able to boost the performance on the minority class samples. Experiments on the NLP&CC2012 Chinese microblog evaluation data set demonstrated that reserved self-training outperforms the best run by 2.06% macro-averaged and 2.30% microaveraged F-measure, respectively.