DialogueRNN: An Attentive RNN for Emotion Detection in Conversations

Emotion detection in conversations is a necessary step for a number of applications, including opinion mining over chat history, social media threads, debates, argumentation mining, understanding consumer feedback in live conversations, etc. Currently, systems do not treat the parties in the conversation individually by adapting to the speaker of each utterance. In this paper, we describe a new method based on recurrent neural networks that keeps track of the individual party states throughout the conversation and uses this information for emotion classification. Our model outperforms the state of the art by a significant margin on two different datasets.

PDF Abstract
Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Emotion Recognition in Conversation CPED DialogueRNN Accuracy of Sentiment 48.57 # 8
Macro-F1 of Sentiment 44.11 # 7
Emotion Recognition in Conversation IEMOCAP DialogueRNN Weighted-F1 63.5 # 45
Accuracy 63.5 # 25
Emotion Recognition in Conversation MELD DialogueRNN Weighted-F1 57.03 # 57
Accuracy 59.54 # 16
Emotion Recognition in Conversation SEMAINE DialogueRNN MAE (Valence) 0.168 # 3
MAE (Arousal) 0.165 # 3
MAE (Expectancy) 0.175 # 3
MAE (Power) 7.9 # 3


No methods listed for this paper. Add relevant methods here