• Indu Bala
• Dr. Sunita Mahajan
• Dr. Ikvinderpal SIngh

The surge of fake news across digital platforms has emerged as a pressing concern in contemporary times, jeopardizing the authenticity of public conversations and societal unity. We present anextensive examination and comparative analysis of feature extraction techniques One Hot, Bag of Words, Term Frequency-Inverse Document Frequency, and Word2Vec using two popular learning models: Multinomial Naive Bayes and LSTM. Multinomial Naive Bayes (Multinomial NB) is a variant of the Naive Bayes classifier, particularly well-suited for text classification tasks, including fake news detection, while LSTM is a type of recurrent neural network (RNN) capable of capturing sequential dependencies in textual data. We evaluate the performance of these models across different feature extraction methods using standard evaluation metrics. This paper provides valuable insights into the effectiveness of various feature extraction techniques for fake news detection, offering practical guidance for researchers and practitioners in the field.

LSTM (Long short-term memory); MultinominalNB (Multinomial Naive Bayes classifier); Kaggle; RNN (Recurrent neural network); one hot; TFIDF(Frequency-inverse document frequency); word2vec; BoW (Bag of Words)

"COMPARATIVE ANALYSIS OF VARIOUS FEATURE EXTRACTION TECHNIQUES USING LEARNING ALGORITHMS", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.12, Issue 5, page no.l662-l667, May 2025, Available :http://www.jetir.org/papers/JETIR2505C67.pdf

"COMPARATIVE ANALYSIS OF VARIOUS FEATURE EXTRACTION TECHNIQUES USING LEARNING ALGORITHMS", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.12, Issue 5, page no. ppl662-l667, May 2025, Available at : http://www.jetir.org/papers/JETIR2505C67.pdf