Emotion Recognition for Vietnamese Social Media Text

@article{Ho2019EmotionRF,
  title={Emotion Recognition for Vietnamese Social Media Text},
  author={Vong Anh Ho and Duong Nguyen and Danh Hoang Thanh Nguyen and Linh Thi-Van Pham and Duc-Vu Nguyen and Kiet Van Nguyen and Ngan Luu-Thuy Nguyen},
  journal={ArXiv},
  year={2019},
  volume={abs/1911.09339}
}
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… 
Exploiting Vietnamese Social Media Characteristics for Textual Emotion Recognition in Vietnamese
TLDR
The experimental evaluation shows that with appropriate pre-processing techniques based on Vietnamese social media characteristics, Multinomial Logistic Regression achieves the best F1-score of 64.40%, a significant improvement over the CNN model built by the authors of UIT-VSMEC.
REAL-TIME EMOTION RECOGNITION OF TWITTER POSTS USING A HYBRID APPROACH
TLDR
This model is a hybrid approach that uses a combination of keyword-based and learning-based models to perform textual emotion recognition on Twitter posts obtained in real-time and shows that the proposed model performs better in comparison to the traditional Unison model.
Span Detection for Aspect-Based Sentiment Analysis in Vietnamese
TLDR
A new Vietnamese dataset (UIT-ViSD4SA) consisting of 35,396 human-annotated spans on 11,122 feedback comments is presented for evaluating the span detection in aspect-based sentiment analysis and a novel system using Bidirectional Long Short-Term Memory (BiLSTM) with a Conditional Random Field (CRF) layer is proposed.
SA2SL: From Aspect-Based Sentiment Analysis to Social Listening System for Business Intelligence
TLDR
This paper creates UITViSFD, a Vietnamese Smartphone Feedback Dataset as a new benchmark corpus built based on a strict annotation schemes for evaluating aspect-based sentiment analysis, consisting of 11,122 human-annotated comments for mobile e-commerce, which is freely available for research purposes.
Comparison Between Traditional Machine Learning Models And Neural Network Models For Vietnamese Hate Speech Detection
TLDR
An ensemble method is proposed that concentrates the abilities of traditional methods and deep learning methods forhate-speech detection on social network language in Vietnamese.
XLM-EMO: Multilingual Emotion Prediction in Social Media Text
TLDR
A multilingual emotion prediction model for social media data, XLM-EMO, shows competitive performance in a zero-shot setting, suggesting it is helpful in the context of low-resource languages.
Constructive and Toxic Speech Detection for Open-domain Social Media Comments in Vietnamese
TLDR
A system for constructive and toxic speech detection with the state-of-the-art transfer learning model in Vietnamese NLP as PhoBERT is proposed and can solve some problems on the online discussions and develop the framework for identifying constructiveness and toxicity Vietnamese social media comments automatically.
A simple and efficient ensemble classifier combining multiple neural network models on social media datasets in Vietnamese
TLDR
This study aims to classify Vietnamese texts on social media from three different Vietnamese benchmark datasets, using CNN, LSTM, and their variants and proposes an ensemble model, combining the highest-performance models.
LDA-Based Topic Modeling Sentiment Analysis Using Topic/Document/Sentence (TDS) Model
TLDR
An unsupervised machine learning approach is applied to discover sentiment polarity not only at the document level but also at the word level, based on joint sentiment topic (JST) and latent Dirichlet allocation (LDA) topic modeling techniques.
Vietnamese Complaint Detection on E-Commerce Websites
TLDR
This paper builds a Vietnamese Open-domain Complaint Detection dataset (UIT-ViOCD), including 5,485 human-annotated reviews on four categories about product reviews on e-commerce sites, and aims to build a system for open-domain complaint detection on E-commerce websites.
...
...

References

SHOWING 1-10 OF 32 REFERENCES
Decision support with text-based emotion recognition: Deep learning for affective computing
TLDR
This work adapts recurrent neural networks from the field of deep learning to affective computing and extends these networks for predicting the score of different affective dimensions, and implements transfer learning for pre-training word embeddings.
UIT-VSFC: Vietnamese Students’ Feedback Corpus for Sentiment Analysis
TLDR
The methods of building annotation guidelines and ensure the annotation accuracy and consistency of this corpus, a free and high-quality corpus for research on two different tasks: sentiment-based and topic-based classifications.
VLSP SHARED TASK: SENTIMENT ANALYSIS
TLDR
The built datasets as well as the evaluation results of the systems participating to the VLSP shared task on Sentiment Analysis for Vietnamese are described.
Using Hashtags to Capture Fine Emotion Categories from Tweets
TLDR
It is shown that emotion‐word hashtags are good manual labels of emotions in tweets and a method to generate a large lexicon of word–emotion associations from this emotion‐labeled tweet corpus is proposed, which is the first lexicon with real‐valued word‐emotion association scores.
#Emotional Tweets
TLDR
This paper describes how a Twitter emotion corpus is created from Twitter posts using emotion-word hashtags, and extracts a word-emotion association lexicon that leads to significantly better results than the manually crafted WordNet Affect lexicon in an emotion classification task.
IEST: WASSA-2018 Implicit Emotions Shared Task
TLDR
A shared task where systems have to predict the emotions in a large automatically labeled dataset of tweets without access to words denoting emotions, and is called the Implicit Emotion Shared Task (IEST) because the systems has to infer the emotion mostly from the context.
A Multi-emotion Classification Method Based on BLSTM-MC in Code-Switching Text
TLDR
A Bidirectional Long-Short Term Memory Multiple Classifiers (BLSTM-MC) model is proposed to study the five classification problems in code-switching text, and obtains text contextual relations through BLSTm-MC model.
Variants of Long Short-Term Memory for Sentiment Analysis on Vietnamese Students’ Feedback Corpus
TLDR
According to the experimental results, the Dependency Tree-LSTM were not better than the LSTM model, however, when combining final hidden state vectors of L STM and Dependency tree-L STM models with a Support Vector Machine classifier, the F1-score of 90.2%, which is higher than the performance of the LstM model.
Sentiment, emotion, purpose, and style in electoral tweets
Deep Learning versus Traditional Classifiers on Vietnamese Students’ Feedback Corpus
TLDR
A sentiment analysis application analyzing student feedback will help the institution to recognize students’ opinions about a problem and identify shortcomings that still exist and the institution can propose an appropriate method to improve the quality of training activities in the future.
...
...