Authors : Kavuru.Pavani; Katam.Kusuma; Medicharla. Hema Venkata Lakshmi

Volume/Issue : Volume 9 - 2024, Issue 2 - February

Google Scholar : https://tinyurl.com/bde87ded

Scribd : https://tinyurl.com/56zx6dj6

DOI : https://doi.org/10.5281/zenodo.10753941

Abstract : Reviews from customers are now an integral part of most online e-commerce (Social media , amazon ,Flipkart, meesho) Companies for their daily operations. customers reviews are becoming a major factor in determining what consumer decide to buy. For analyzing the growth of e-commerce companies based on customer reviews or feedback. Organizations typically don’t have the time or resource to scour the internet and read and analyse every piece of data relating to their products, services and brand . Sentiment analysis is an important way for organizations to understand how customers perceive and experience their products and brands. Increasingly, customer feedback is given online through a variety of unconnected platforms, such as Amazon product reviews and posts on social media platforms. In e-commerce Companies, there are huge amount of reviews it is difficult to measure their growth based on these customer reviews .In this we are using SENTIMENT ANALYSIS (SA) is a machine learning algorithm is used to determine whether a given text contains positive(excellent, good ),negative(bad, wrost) or neutral comments(average). Sentiment analysis ,also knowns as opinion mining , is the process of extracting subjective information from text and determining the sentiment expressed within it .It is a text of NPL(natural language processing) . IIn the context of product reviews data , sentiment analysis involves understanding the emotions and opinions of customers towards specific products or brands . In the Sentiment Analysis spilt into various types like Emotion Detection(ED), Aspect Based Sentimental Analysis (ABSA), Fine Grained Sentimental Analysis(FGSA) , Multilingual Sentimental Analysis (MSA).These types are used to analyse the customer reviews is either positive or negative .Emotion detection is the process of identifying human emotion. ED is widely helpful for recognizing the emotions of other .Aspect based sentimental analysis is Breaks down text into aspects (component of products), and then allocates each one a sentimental level(positive ,negative ,neutral).Fine grained sentimental analysis is done at text and sentence level . Multingual sentimental analysis done in multiple languages and also done by the use of complex neural network architecture. The techniques in sentiment analysis are logistic regression, naivebayes, random forest classifier, SVM(support vector machine) etc. By analyzing the sentimental expressed in these reviews, businesses can gain a comprehensive understanding of how their product are perceived by customers.

Keywords : Sentiment Analysis; Logistic Regression ;Naive Bayes ;Random Forest; SVM.