How to improve ML Model Accuracy for Text Classification?

Hi Experts,

We are dealing with Text Classification Problem. We have around 80K records with around 50 classes. The data is highly imbalanced. It has 2 columns one for description and other contains class.
Till now we have tried following models and techniques:

1. Data Preprocessing: a. Lowercase conversion, removed numeric texts, removed punctuations b. Removed unimportant words and stop words c. Lemmatization
2. TFIDF transformation
3. Using SKLEARN Models: a. Linear SVC b. Linear Regression c. Logistic Regression d. Decision Trees e. Random Forest
4. Using Huggingface Transformers: a. Google Bert b. Distil Bert
5. SMOTE sampling

It is observed that the maximum accuracy we got is 70% (Random Forest and Google Bert).
Is there any scope to improve accuracy?
If yes, what other techniques or models we can use to improve accuracy?

The above is the detailed content of How to improve ML Model Accuracy for Text Classification?. For more information, please follow other related articles on the PHP Chinese website!