EMOTION REGCONITION FOR VIETNAMESE SOCIAL MEDIA TEXT

MainPackages:

- Pandas (1.1.3)
- Selenium (3.141.0)
- Scikit-learn (0.23.2)
- Underthesea (1.3.1)

Introductions:

- Crawling data from 3 youtube videos (100 comments for each video) (*)
- Data preprocessing (stopwords, word segmentation)
- Label emotions (Disgust,Enjoyment,Anger,Surprise,Sadness,Fear,Other)
- Trainning datasets of UIT-VSMEC. Report performance metrics.
- Applying trained model to 3 datasets of (*). Report performance metrics.

Requirements:

- Python(≥3.6),NumPy(≥1.13.3),SciPy(≥0.19.1),Joblib(≥0.11),Threadpoolctl(≥2.0.0)
- Torch(1.5.0),Torchvision(0.7.0)

Notes:

- Make sure 'chromedriver.exe' is in the same location as 'Datamining.ipynb'
- The folder 'dataList' contains all the datasets of the youtube video. 

References:

• From Books&Paper:
[1]: J.Han, M.Kamber, J.Pei, [2011], Data Mining Concepts and Techniques 3rd Edition, Illinois University, Urbana-Champaign, 83-123.
[2]: S.A.Alasadi, W.S.Bhaya , [2017], Review of data preprocessing techniques in datamining, College of Information Technology, Iraq, 4102–4107.
[3]: Scikit-learn Developers, [2020], Scikit-learn User guide - Release 0.23.2, 1930-1948.
[4]: V.A.Ho, D.H.-C.Nguyen, D.H.Nguyen, L.T.-V.Pham, D.V.Nguyen, K.V.Nguyen, N.L-T.Nguyen, [2019], Emotion Recognition for Vietnamese Social Media Text.

• From Internet:
[5]: https://www.geeksforgeeks.org/feature-extraction-techniques-nlp/
[6]: https://www.geeksforgeeks.org/data-preprocessing-in-data-mining/
[7]: https://scikit-learn.org/stable/modules/feature_extraction.html
[8]: https://programmersought.com/article/61456088337/
[9]: https://pypi.org/project/underthesea/