There are several commonly used techniques for feature extraction in text classification. Here are some of them:

  1. Bag of Words (BoW): BoW is one of the simplest techniques for feature extraction, where each document is represented by a vector of word frequencies. This method ignores the order and structure of the words in the document.

  2. Term Frequency-Inverse Document Frequency (TF-IDF): TF-IDF is a technique that assigns weights to words based on their frequency in a document and their rarity across all documents. It helps to capture the importance of words in a document compared to the corpus.

  3. Word2Vec: Word2Vec is a popular word embedding technique that represents words in a continuous vector space. It captures the semantic meaning of words by mapping similar words to similar vectors. Word2Vec models can be pre-trained on large corpora or trained on the specific task data.

  4. GloVe: Global Vectors for Word Representation (GloVe) is another word embedding technique that creates word vectors based on the co-occurrence statistics of words in a large corpus. It captures the global relationships between words.

  5. n-grams: n-grams are contiguous sequences of n words. They can capture the local syntactic and semantic information in a document. Common choices include unigrams (single words), bigrams (two-word sequences), and trigrams (three-word sequences).

  6. Part-of-Speech (POS) tagging: POS tagging assigns a grammatical category (such as noun, verb, adjective) to each word in a document. It can provide useful linguistic information that can be used as features in text classification.

  7. Word frequency: Calculating the frequency of each word in a document can be a simple yet effective feature extraction technique. It can capture the relative importance of words in different documents.

  Each of these techniques has its own advantages and drawbacks. The choice of technique depends on the specific task, the available data, and the desired balance between simplicity and complexity in feature representation. Most text classification models use a combination of these techniques to extract meaningful features from text.