Emotion Annotation Using Hierarchical Aligned Cluster Analysis

The correctness of annotation is quite important in supervised learning, especially in electroencephalography(EEG)-based emotion recognition. The conventional EEG annotations for emotion recognition are based on the feedback like questionnaires about emotion elicitation from subjects. However, these methods are subjective and divorced from experiment data, which lead to inaccurate annotations. In this paper, we pose the problem of annotation optimization as temporal clustering one. We mainly explore two types of clustering algorithms: aligned clustering analysis (ACA) and hierarchical aligned clustering analysis (HACA). We compare the performance of questionnaire-based, ACAbased, HACA-based annotation on a public EEG dataset called SEED. The experimental results demonstrate that our proposed ACA-based and HACA-based annotation achieve an accuracy improvement of 2.59% and 4.53% in average, respectively, which shows their effectiveness for emotion recognition.