Interdisciplinary knowledge‐based implicit emotion recognition
Jialin Jiang, Xinzhi Wang, Xiangfeng Luo · Concurrency and Computation Practice and Experience · 2020
Summary Detecting different emotions is a key step toward intelligent recommendation and affective computing, which plays an increasingly important role in guiding decisions. There have been a large number of previous work of machine learning in this topic. However, most existing methods neglect the help of long‐term accumulated and precious interdisciplinary knowledge, which cover both computer science and psychology. In this work, we distill part of the psychological knowledge as following: (i) The emotions with the same polarity co‐occur frequently, while emotions with contrary polarity co‐exist hardly; (ii) The relations between emotions are variable and complicated; (iii) The number of emotions that can be aroused in the same moment is limited. In this paper, we propose two novel modules to execute above prior knowledge, by adding external constraints to our proposed model Double Attention Convolutional Neural Network. In the first module, the emotion relationships are captured by an automatically extracted emotion template. In the second module, uncertainty punishment is applied to limit the too frequent emotions. Our proposed model, which employs interdisciplinary knowledge, performs potentially and get state‐of‐the‐art result when compared with models without above constraints.