Annotation and Detection of Emotion in Text-based Dialogue Systems with CNN
This addresses emotion recognition in text-based dialogue systems to improve human-computer interaction, though it appears incremental with a focus on Chinese language.
The authors tackled emotion detection in Chinese daily dialogues by developing EmoNet, a deep convolutional neural network that avoids segmentation and keyword extraction to preserve linguistic features, achieving better results than state-of-the-art detectors.
Knowledge of users' emotion states helps improve human-computer interaction. In this work, we presented EmoNet, an emotion detector of Chinese daily dialogues based on deep convolutional neural networks. In order to maintain the original linguistic features, such as the order, commonly used methods like segmentation and keywords extraction were not adopted, instead we increased the depth of CNN and tried to let CNN learn inner linguistic relationships. Our main contribution is that we presented a new model and a new pipeline which can be used in multi-language environment to solve sentimental problems. Experimental results shows EmoNet has a great capacity in learning the emotion of dialogues and achieves a better result than other state of art detectors do.