Mutual Supervised Fusion & Transfer Learning with Interpretable Linguistic Meaning for Social Data Analytics

Abstract

Social data analytics is often taken as the most commonly used method for community discovery, product recommendations, knowledge graph, and so on. In this study, social data are firstly represented in different feature spaces by using various feature extraction algorithms. Then we build a transfer learning model to leverage knowledge from multiple feature spaces. During modeling, since the assumption that the training and the testing data have the same distribution is always true, we give a theorem and its proof which asserts the necessary and sufficient condition for achieving a minimum testing error. We also theoretically demonstrate that maximizing the classification error consistency across different feature spaces can improve the classification performance. Additionally, the cluster assumption derived from semi-supervised learning is introduced to enhance knowledge transfer. Finally, aTagaki-Sugeno-Kang (TSK)fuzzy system-based learning algorithm is proposed, which can generate interpretable fuzzy rules. Experimental results not only demonstrate the promising social data classification performance of our proposed approach but also show its interpretability which is missing in many other models.