• Jaffarhussain A
• N S Sandhya
• Shashank M
• Sindhu A
• Dr. Jithendra PR Nayak

This project focuses on automated learning techniques and analyses of emotions based on deep learning to classify positive, negat ive, or neutral emotion textbooks. The analysis is performed using data records such as GosarchSearch and Sentmenta140. The co llected data is suffered by extensive preprocessing, including improving model accuracy using techniques such as text cleaning, to kenization, stop word removal, TF-IDF, Word Bags (ARC), and Word Instruments (Word2vec, Glove, Bert). Numerous auto- learning models including logistics crowds, Vector (SVM) support, Nyver Bayes, Random Forest, and more. According to the mo del, the model is evaluated with power metrics such as accuracy, accuracy, memory, and score F1, providing an essential assessm ent of effectiveness in classifying emotions. This project not only explores theoretical and practical aspects of emotional analysis, but also shows actual applications in social networking, brand reputation management, product check analysis, and interpretation of customer comments. Furthermore, this study highlights the importance of distinctive extraction techniques, optimizing model s election and performance, and optimizing performance in achieving solid classification of emotions..

SENTIMENT ANALYSIS USING MACHINE LEARNING

"SENTIMENT ANALYSIS USING MACHINE LEARNING", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.12, Issue 7, page no.41-45, July-2025, Available :http://www.jetir.org/papers/JETIRGX06008.pdf

"SENTIMENT ANALYSIS USING MACHINE LEARNING", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.12, Issue 7, page no. pp41-45, July-2025, Available at : http://www.jetir.org/papers/JETIRGX06008.pdf