How emoji and word embedding helps to unveil emotional transitions during online messaging

TL;DR

This paper explores how emoji and word embeddings can be integrated with Affect Control Theory to model and detect emotional transitions in online messaging sessions with chatbots.

Contribution

It introduces a novel framework that extends affective dictionaries with emoji embeddings to better understand emotional dynamics during online chats.

Findings

Framework successfully detects emotional changes during messaging

Emoji embeddings enhance emotion prediction accuracy

Affective dictionaries can be extended with emoji representations

Abstract

During online chats, body-language and vocal characteristics are not part of the communication mechanism making it challenging to facilitate an accurate interpretation of feelings, emotions, and attitudes. The use of emojis to express emotional feeling is an alternative approach in these types of communication. In this project, we focus on modeling a customer's emotion in an online messaging session with a chatbot. We use Affect Control Theory (ACT) to predict emotional change during the interaction. To let the customer use emojis, we also extend the affective dictionaries used by ACT. For this purpose, we mapped Emoji2vec embedding to the affective space. Our framework can find emotional change during messaging and how a customer's reaction is changed accordingly.