• S.Sadhiya
• Dr.N.Rahul Pal

sentiment analysis has emerged as a crucial technique for comprehending consumer opinions and feedback. This research article employs the Naive Bayes technique to apply sentiment analysis to Amazon electronic product reviews, specifically for Amazon's Alexa devices. By dividing product reviews into three categories—positive, negative, and neutral—the study hopes to gain a better picture of how customers feel about Alexa's functionality, performance, and usability. Because of its ease of use, effectiveness, and capacity to manage huge datasets, the Naive Bayes classifier—a probabilistic machine learning algorithm—is employed. The study takes a methodical approach, first gathering a sizable dataset of Alexa product reviews from Amazon and then preparing the data. Naive Bayes is used to classify sentiment, and evaluation criteria including accuracy, precision,recall and F1-score, which are used to gauge the model's effectiveness. The results of this study advance the field of sentiment analysis in e-commerce and provide Amazon and other businesses with useful information to enhance their product offers based on customer input. In the end, the study shows that it is feasible to process and analyze customer evaluations in a useful, scalable way using machine learning techniques.

Sentimental Analysis, Naïve Bayes Algorithm.

"Sentimental Analysis Of Amazon Electronic Product Reviews Using Naive Bayes On Alexa", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.12, Issue 1, page no.c189-c200, January-2025, Available :http://www.jetir.org/papers/JETIR2501223.pdf

"Sentimental Analysis Of Amazon Electronic Product Reviews Using Naive Bayes On Alexa", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.12, Issue 1, page no. ppc189-c200, January-2025, Available at : http://www.jetir.org/papers/JETIR2501223.pdf