Author Login IJIRT Partner Network (IPN) Login

Aspect Based Sentiment Analysis of Beauty Product Review using Machine Learning Algorithm

  • Unique Paper ID: 178784
  • Volume: 11
  • Issue: 12
  • PageNo: 5149-5153
  • Abstract:
  • The proliferation of online beauty product reviews has given rise to the need for more nuanced sentiment analysis approaches. This study focuses on aspect-based sentiment analysis (ABSA) of skincare product reviews using the XGBoost machine learning algorithm. Utilizing the Sephora Skincare Reviews dataset, the analysis targets the 10 most-reviewed products to extract key aspects such as packaging, price, scent, texture, and effectiveness. Each aspect is then classified according to sentiment polarity: positive, negative, or neutral. Unlike traditional sentiment analysis, ABSA provides fine-grained insights by associating sentiments with specific product attributes, enabling better decision-making for both consumers and businesses. XGBoost was selected for its efficiency and high performance in handling structured data and imbalanced class distributions. The system pipeline includes data preprocessing, aspect extraction using rule-based and frequency-based methods, sentiment labeling, and classification. Results indicate that XGBoost, when tuned with optimal hyperparameters and trained on selected aspects, achieves strong performance across multiple sentiment classes. Accuracy achived 83%.This approach demonstrates the potential of using advanced machine learning models for detailed opinion mining in e-commerce domains, especially for consumer-centric industries such as beauty and skincare. Future work will explore deep learning approaches and hybrid models for improved accuracy in aspect detection and sentiment classification.
Download article email to a friend

Cite This Article

  • ISSN: 2349-6002
  • Volume: 11
  • Issue: 12
  • PageNo: 5149-5153

Aspect Based Sentiment Analysis of Beauty Product Review using Machine Learning Algorithm

Related Articles

28 Dec, 2024

A Review on Sentiment Analysis of Product Reviews Using Machine Learning Techniques

Read More
Impact Factor
8.01 (Year 2024)
UGC Approved
Journal no 47859

Join Our IPN

IJIRT Partner Network

Submit your research paper and those of your network (friends, colleagues, or peers) through your IPN account, and receive 800 INR for each paper that gets published.

Join Now

Latest Publication

Archive

View More

Recent Conferences

NCSEM 2024

National Conference on Sustainable Engineering and Management - 2024 Last Date: 15th March 2024

Submit inquiry