SocialNLP EmotionX 2019 Challenge Overview: Predicting Emotions in Spoken Dialogues and Chats

TL;DR

The paper overviews the EmotionX 2019 Challenge focused on predicting emotions in spoken and chat dialogues, highlighting datasets, participant engagement, and top performance results.

Contribution

It introduces the EmotionX 2019 Challenge, datasets, and summarizes participant methods and performance in emotion prediction tasks.

Findings

Top micro-F1 score of 81.5% on spoken dialogues

Top micro-F1 score of 79.5% on chat dialogues

36 teams registered, 11 submitted predictions

Abstract

We present an overview of the EmotionX 2019 Challenge, held at the 7th International Workshop on Natural Language Processing for Social Media (SocialNLP), in conjunction with IJCAI 2019. The challenge entailed predicting emotions in spoken and chat-based dialogues using augmented EmotionLines datasets. EmotionLines contains two distinct datasets: the first includes excerpts from a US-based TV sitcom episode scripts (Friends) and the second contains online chats (EmotionPush). A total of thirty-six teams registered to participate in the challenge. Eleven of the teams successfully submitted their predictions performance evaluation. The top-scoring team achieved a micro-F1 score of 81.5% for the spoken-based dialogues (Friends) and 79.5% for the chat-based dialogues (EmotionPush).