EMOTION RECOGNITION IN TEXT
GOAL
To develop a model that can analyze text data and classify the emotions expressed (e.g., happiness, sadness, anger).
DATASET
https://www.kaggle.com/datasets/pashupatigupta/emotion-detection-from-text
DESCRIPTION
To analyze the dataset of emotion detction from text and build,train the model on the basis of different features and variables.
Visualization and EDA of different attributes:
WHAT I HAD DONE
1.Load the dataset which contains about 40000 entires.
2.Checked for missing values and cleaned the data accordingly.
3.Analyzed the data, found insights and visualized them accordingly.
4.Plotting distribution graphs to find corelations.
5.Found detailed insights of different columns with target variable using plotting libraries.
6.Trained the datasets by different models and saves their accuracies into a dataframe.
MODELS USED
Random forest classifier as it shows high accuracy,versatility and scalability.
Gradient booster which is a strong algorithm for classification and regression problems
XGBClassifier help to improve machine-learning model's accuracy.
LIBRARIES NEEDED
Numpy
Pandas
Word cloud
Matplotlib
Seaborn
Scikit-Learn
Scipy
Xgboost
Tensorflow
Keras
VISUALIZATION
INCLUSION OF IMAGES OF THE VISUALIZATION IS MUST (RESULT OF EDA).
ACCURACIES
Random forest classifier Score = 1.0
Gradient booster Score = 1.0
XGBClassifier Score = 0.25
CONCLUSION
Random forest classifier and Gradient booste rmodels show promising performance .
XGBClassifier shows less accuracy
YOUR NAME
SRUJANA