Team - Dy.Tech

Team Members

Amar Parab	Simeen Pathan	Dhanashri Petkar	Sania Alam
Class - TY A	Class - TY A	Class - TY A	Class - TY A
Roll No. - 39	Roll No. - 35	Roll No. - 02	Roll No. - 17

College - D.Y.Patil College of Engineering & Technology

##PROJECT TITTLE ###movielens_recommendations_transformers

---

##USE OF REAL DATASET

###Project Structure

• Uploading and Reading the Dataset: Upload the dialogue transcript and read it into a pandas DataFrame.
• Preprocessing the Data: Clean and preprocess the data for training, including encoding emotions and normalizing VAD (Valence, Arousal, Dominance) scores.
• Tokenization: Tokenize the input text using BERT tokenizer.
• Custom Dataset Class: Create a custom dataset class to handle input encodings and labels.
• Model Training: Train a BERT model for sequence classification using the prepared dataset.
• Model Evaluation: Evaluate the trained model on the dataset.