WEMOTE - Word Embedding based Minority Oversampling Technique for Imbalanced Emotion and Sentiment Classification

Imbalanced training data always puzzles the supervised learning based emotion and sentiment classification. Several existing research showed that data sparseness and small disjuncts are the two major factors affecting the classification. Target to these two problems, this paper presents a word embedding based oversampling method. Firstly, a large-scale text corpus is used to train a continuous skip-gram model in order to form word embedding. A feature selection and linear combination algorithm is developed to construct text representation vector from word embedding. Based on this, the new minority class training samples are generated through calculating the mean vector of two text representation vectors in the same class until the training samples for each class are the same so that the classifiers can be trained on the fully balanced dataset. Evaluations on NLP&CC2013 Chinese micro blog emotion classification (multi-label) and English Multi-Domain Sentiment Dataset version 2.0 (single label) show that the proposed oversampling approach improves the imbalanced emotion/sentiment classification in Chinese (sentence level) and English (document level) obviously. Further analysis show that our approach can reduce the affection of data sparseness and small disjuncts in imbalanced emotion and sentiment classification.