Emotion Detection on TV Show Transcripts with Sequence-based Convolutional Neural Networks
This work addresses the problem of under-explored text-based emotion detection for researchers in natural language processing, though it is incremental as it builds on existing methods for document classification.
The paper tackled emotion detection in text from TV show dialogues by introducing a new corpus annotated with seven emotions and developing sequence-based convolutional neural network models with attention, achieving accuracies of 37.9% for fine-grained and 54% for coarse-grained emotions.
While there have been significant advances in detecting emotions from speech and image recognition, emotion detection on text is still under-explored and remained as an active research field. This paper introduces a corpus for text-based emotion detection on multiparty dialogue as well as deep neural models that outperform the existing approaches for document classification. We first present a new corpus that provides annotation of seven emotions on consecutive utterances in dialogues extracted from the show, Friends. We then suggest four types of sequence-based convolutional neural network models with attention that leverage the sequence information encapsulated in dialogue. Our best model shows the accuracies of 37.9% and 54% for fine- and coarse-grained emotions, respectively. Given the difficulty of this task, this is promising.