Emotion Recognition for Vietnamese Social Media Text

TL;DR

This paper introduces a new Vietnamese social media emotion corpus and evaluates machine learning models, with CNN achieving the best performance in emotion recognition for Vietnamese text.

Contribution

It creates the first standard Vietnamese social media emotion corpus and benchmarks various models for emotion recognition in Vietnamese.

Findings

CNN achieved a weighted F1-score of 59.74%.

The UIT-VSMEC corpus contains 6,927 emotion-annotated sentences.

The corpus is publicly available for further research.

Abstract

Emotion recognition or emotion prediction is a higher approach or a special case of sentiment analysis. In this task, the result is not produced in terms of either polarity: positive or negative or in the form of rating (from 1 to 5) but of a more detailed level of analysis in which the results are depicted in more expressions like sadness, enjoyment, anger, disgust, fear, and surprise. Emotion recognition plays a critical role in measuring the brand value of a product by recognizing specific emotions of customers' comments. In this study, we have achieved two targets. First and foremost, we built a standard Vietnamese Social Media Emotion Corpus (UIT-VSMEC) with exactly 6,927 emotion-annotated sentences, contributing to emotion recognition research in Vietnamese which is a low-resource language in natural language processing (NLP). Secondly, we assessed and measured machine learning and deep neural network models on our UIT-VSMEC corpus. As a result, the CNN model achieved the highest performance with the weighted F1-score of 59.74%. Our corpus is available at our research website.