Active Deep Networks for Semi-Supervised Sentiment Classification

This paper presents a novel semisupervised learning algorithm called Active Deep Networks (ADN), to address the semi-supervised sentiment classification problem with active learning. First, we propose the semi-supervised learning method of ADN. ADN is constructed by Restricted Boltzmann Machines (RBM) with unsupervised learning using labeled data and abundant of unlabeled data. Then the constructed structure is finetuned by gradient-descent based supervised learning with an exponential loss function. Second, we apply active learning in the semi-supervised learning framework to identify reviews that should be labeled as training data. Then ADN architecture is trained by the selected labeled data and all unlabeled data. Experiments on five sentiment classification datasets show that ADN outperforms the semi-supervised learning algorithm and deep learning techniques applied for sentiment classification.