How have you implemented text classification tasks?

For text classification tasks, I usually use the following approach:

1. Preprocessing: cleaning of unnecessary characters, tokenization, converting to lowercase.
2. Vectorization: transforming text into a numerical format using TF-IDF, CountVectorizer, or embeddings (e.g., Word2Vec, FastText).
3. Model selection: for simple tasks — logistic regression, naive Bayes, SVM; for more complex tasks — neural networks (LSTM, Transformer).
4. Training and evaluation: splitting data into training and testing sets, hyperparameter tuning, metric evaluation (accuracy, F1).

Example using sklearn and TF-IDF:

from sklearn.feature_extraction.text import TfidfVectorizer
from sklearn.linear_model import LogisticRegression
from sklearn.pipeline import make_pipeline

texts = ["Example text 1", "Another example"]
labels = [0, 1]

model = make_pipeline(TfidfVectorizer(), LogisticRegression())
model.fit(texts, labels)

prediction = model.predict(["New text for classification"])
print(prediction)