README.md

DS202 / Data science thesis 1

About

• This is a college course project about collecting social data from Internet for for NLP emotion classification task.
• Techniques applied:

• Data collection and cleaning
• Annotation guildlines
• Word tokenization, Deep learning models

Table of contents

• DS200.L21 / Big data

• About
• Table of contents
• Data source
• Experiment pipelines
• Data details
• Code
• Presentation slides and Report
• References
• Cite us

Data source

• Raw data
• Clean data

Experiment pipelines

Data details

• Label distribution

• Word count

• Comment length distribution over labels

• Annotation agreement results over 5 rounds

Code

• Feature extraction and models training (and so on) in this repo are implemented in Google Colab.
• All codes are organized in name.ipynb files.

Presentation slides and Report

• Report slides
• Report
• Guildlines

References

• All references are cited in the report file.

Cite us

@INPROCEEDINGS{9997964,
  author={Van Duong, Binh and Nguyen, An Trong and Ha, Chien Nhu and Duong, Hong-Hanh Thi and Tran, My-Linh Thi and Do, Trong-Hop},
  booktitle={2022 25th Conference of the Oriental COCOSDA International Committee for the Co-ordination and Standardisation of Speech Databases and Assessment Techniques (O-COCOSDA)}, 
  title={UIT-VLFC: Vietnamese Lipstick Feedbacks Corpus}, 
  year={2022},
  volume={},
  number={},
  pages={1-5},
  doi={10.1109/O-COCOSDA202257103.2022.9997964}}