- Task: Text binary/multi classification
- Base model: Tree model(e.g. DecisionTree, RandomForest, XGBoost)
- Input data
- Binary: Naver sentiment movie corpus
- Multiple
- Output data
- Binary: Positive/Negative
- Multiple
- Period: 2022.04.13 - 2022.05.13
- Implementation plan
- Build a minimal viable text classification model
- Train the model and set up the baseline score
- Build a data pipeline
- Automate the process of training and evaluating the model on the data
- Choose other advanced tree model and implement it on process
- Compare the performance of the model with the baseline score