Enhancing Sentiment Analysis in Electronic Product Reviews Using Machine Learning Algorithms

Authors

  • Mohandas Archana
  • Thambusamy Velmurugan

Abstract

In the era of electronic commerce, understanding customer sentiments through product reviews has become crucial for the smooth running of businesses. In this research work, thorough investigation of sentiment analysis in the electronic product reviews dataset, which is collected from the Flipkart and some other social media. The aim of this research work is to ascertain the polarity of consumer comments by doing sentiment analysis on text based electronic product reviews. A number of preprocessing methods were applied to the chosen dataset including stemming, tokenization, lemmatization, punctuation removal, and stop word removal. These actions were essential for improving the textual data and getting it ready for the further processing. The text-based data was transformed into a numeric format using vectorization techniques, and the resulting data was then fed into machine learning algorithms to identify sentiments. After that, the dataset was divided into training and testing portions in order to ensure a robust model evaluation. Using machine learning algorithms like Naive Bayes, Support Vector Machine (SVM), Random Forest, and Decision Tree, this work analyzes and classifies sentiment. The objective is to identify significant sentiments within textual reviews and examine the effectiveness and efficiency of the aforementioned machine learning techniques using preprocessed data. The best classification algorithm's performance is indicated by the outcomes it produces, out of all of them.

Downloads

Download data is not yet available.

Downloads

Published

2024-07-10

How to Cite

Mohandas Archana, & Thambusamy Velmurugan. (2024). Enhancing Sentiment Analysis in Electronic Product Reviews Using Machine Learning Algorithms. International Journal of Computer Information Systems and Industrial Management Applications, 16(3), 19. Retrieved from https://cspub-ijcisim.org/index.php/ijcisim/article/view/727

Issue

Section

Original Articles