Emotion analysis of children´s stories with context information

In this paper, we analyse the emotion of children´s stories in sentence level by considering the context information. We demonstrate that the emotion of a sentence is not only dependent on its content, but also affected by its neighbours in a story. A Hidden Markov Model (HMM) based method is proposed to model the emotion sequence and to detect whether a sentence is neutral or not. We show the important features for emotion detection by studying a children´s story corpus. An empirical evaluation is conducted to investigate the efficiency of the model. The results demonstrate that the proposed method can achieve competitive performance with the state-of-the-art methods, and it is affected more slightly by the training set than traditional classification methods. Classifier fusion is applied to combine different methods to achieve better results.