Copyright © 2025 Authors retain the copyright of this article. This article is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

@article{178784,
        author = {Kajal D. Dolar and Rupal J. Shilu and Tosal Bhalodia},
        title = {Aspect Based Sentiment Analysis of Beauty Product Review using Machine Learning Algorithm},
        journal = {International Journal of Innovative Research in Technology},
        year = {2025},
        volume = {11},
        number = {12},
        pages = {5149-5153},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=178784},
        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.},
        keywords = {Aspect-Based Sentiment Analysis (ABSA), Natural Language Processing (NLP), Rule-Based Aspect Extraction, XGBoost.},
        month = {May},
        }