Cold-Start Aware User and Product Attention for Sentiment Classification
This addresses a common issue in review websites where new users or products lack sufficient data, offering an incremental improvement for sentiment classification in such scenarios.
The paper tackles the cold-start problem in sentiment analysis for users/products with limited reviews by proposing HCSC, which uses a Cold-Start Aware Attention mechanism and shared vectors from similar users/products, resulting in significantly better RMSE performance on sparse datasets compared to previous models.
The use of user/product information in sentiment analysis is important, especially for cold-start users/products, whose number of reviews are very limited. However, current models do not deal with the cold-start problem which is typical in review websites. In this paper, we present Hybrid Contextualized Sentiment Classifier (HCSC), which contains two modules: (1) a fast word encoder that returns word vectors embedded with short and long range dependency features; and (2) Cold-Start Aware Attention (CSAA), an attention mechanism that considers the existence of cold-start problem when attentively pooling the encoded word vectors. HCSC introduces shared vectors that are constructed from similar users/products, and are used when the original distinct vectors do not have sufficient information (i.e. cold-start). This is decided by a frequency-guided selective gate vector. Our experiments show that in terms of RMSE, HCSC performs significantly better when compared with on famous datasets, despite having less complexity, and thus can be trained much faster. More importantly, our model performs significantly better than previous models when the training data is sparse and has cold-start problems.