• Rahul
• Siddhali
• Sneha
• Shubhada

Sentiment recognition from audio signal requires module to extract feature and classifier for training. Here we define the feature vector consists of sound packets signal which is differentiate speaker specified features such as pitch, energy, tone, which is important to train the sentiment recognition model to detect and recognize a particular sentiment perfectly. We consider here open source dataset for data training, which is available in English language. Sound vocal tract information, represented by Mel-frequency cepstral coefficients (MFCC), was extracted from the audio samples in training dataset. The pitch or that particular sound extracted, anger, happiness, sad, neutral, etc. Sentiments. The test data extract procedure followed for which of the classifier would make a prediction regarding the underlying sentiment in the test audio.. The paper details the two methods applied on feature vectors and the effect of increasing the number of feature vectors fed to the classifier. Our module provides an accuracy of analytical classification for an Indian English speech. The accuracy for Indian English was 73 percent.

Machine Learning, SVM, Classifier, K-means, Matplotelib, sk-learn, pandas, data analysis

"Analytical Review for Sentiment Recognition – Machine Learning", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.9, Issue 5, page no.d306-d312, May-2022, Available :http://www.jetir.org/papers/JETIR2205457.pdf

"Analytical Review for Sentiment Recognition – Machine Learning", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.9, Issue 5, page no. ppd306-d312, May-2022, Available at : http://www.jetir.org/papers/JETIR2205457.pdf