Hieubeo23/UIT-VSMEC

---
task_categories:
- text-classification
language:
- vi
size_categories:
- 1K<n<10K
---

# Introduction
Emotion recognition is a higher approach or 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 sentiment analysis in which the result are depicted in more expressions like sadness, enjoyment, anger, disgust, fear and surprise. Emotion recognition plays a critical role in measuring 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 about 6,927 human-annotated sentences with six emotion labels, 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. As a result, Convolutional Neural Network (CNN) model achieved the highest performance with 57.61% of F1-score.

---
任务类别：
- 文本分类（text-classification）
语言：
- 越南语
样本量范围：
- 1000 < 样本数 < 10000
---

# 引言
情感识别（Emotion Recognition）属于情感分析（Sentiment Analysis）的高阶研究路径或特殊子类。在该任务中，模型输出结果并非仅基于情感极性（积极或消极）或评分（1至5分）的形式，而是属于更细粒度的情感分析范畴，其结果以诸如悲伤、愉悦、愤怒、厌恶、恐惧与惊讶等多种情感表达形式呈现。通过识别用户评论中的特定情感，情感识别在衡量产品品牌价值方面具有关键作用。

本研究达成了两项核心目标：其一，构建了标准越南语社交媒体情感语料库（Vietnamese Social Media Emotion Corpus, UIT-VSMEC），该语料库包含约6927条经人工标注的句子，涵盖6种情感标签，可为属于低资源自然语言处理（Natural Language Processing, NLP）范畴的越南语情感识别研究提供支撑；其二，在UIT-VSMEC语料库上对机器学习与深度神经网络模型开展了性能评估与测试，最终卷积神经网络（Convolutional Neural Network, CNN）以57.61%的F1分数取得了最优性能。