Building Multi-Task NLP model with LSTM : Detect Emotions, Hate Speech & Violence in Text

Опубликовано: 20 Май 2026
на канале: InsightsByRish

8,487

160

Hey everyone,
In this video I have demonstrated how to build a multi-task NLP model using LSTM.
Multi-task learning (MTL) is a machine learning approach where a model is trained simultaneously on multiple related tasks.

Code File (Github Repository):
https://github.com/RishaRane/Multi_Ta...

Datasets:
(i) Emotion Data:
https://www.kaggle.com/datasets/nelgi...
(ii) Violence Data:
https://www.kaggle.com/datasets/gaura...
(iii) Hate Speech Data:
https://www.kaggle.com/datasets/mrmor...

Medium Article for the same:
/ building-multi-task-nlp-model-using-lstm

Connect with me on Instagram:
/ insightsbyrish

For any queries, mail me on:
[email protected]

TIMESTAMPS:
00:00:00 Starting
00:03:24 1. Loading the Data
00:05:47 2. Data Preprocessing
00:27:20 3. Label Encoding
00:30:52 4. Stopwords Removal
00:37:33 5. Tokenization & Padding
00:46:37 6. Defining Model Architecture
01:09:55 7. Prediction & Evaluation
01:21:58 8. Manual Testing (Inference)

#deeplearning
#naturallanguageprocessing
#nlp
#lstm
#python
#multitasklearning

Thanks for watching!
Please LIKE, SHARE and SUBSCRIBE if you enjoyed the content.