International Journal of Innovative Research in Computer and Communication Engineering
ISSN Approved Journal | Impact factor: 8.771 | ESTD: 2013 | Follows UGC CARE Journal Norms and Guidelines
| Monthly, Peer-Reviewed, Refereed, Scholarly, Multidisciplinary and Open Access Journal | High Impact Factor 8.771 (Calculated by Google Scholar and Semantic Scholar | AI-Powered Research Tool | Indexing in all Major Database & Metadata, Citation Generator | Digital Object Identifier (DOI) |
| TITLE | Multilingual Sentiment Analysis for E-Commerce Product Reviews |
|---|---|
| ABSTRACT | The rapid growth of e-commerce platforms has led to an exponential increase in customer generated textual data, particularly product reviews written in multiple languages. Extracting meaningful insights from this diverse and unstructured data presents a significant challenge for businesses aiming to understand customer satisfaction and improve decision-making. This project, Multilingual Sentiment Analysis For E- Commerce Product Reviews, addresses this challenge by providing an AI-powered system that analyzes customer reviews across different languages and presents actionable insights through an interactive web-based dashboard. The system enables users to upload customer review datasets in CSV or Excel formats and automatically processes them using advanced natural language processing (NLP) techniques. Leveraging large language models, the application detects the language of each review, performs sentiment classification (positive, negative, or neutral), and extracts key phrases that reflect common customer opinions. The processed data is then visualized through intuitive charts, tables, and comparative views, allowing users to easily interpret sentiment trends, language distribution, and customer feedback patterns. The application is built using a modern full-stack architecture, combining a React and TypeScript frontend with a Python-based backend service. It integrates AI services for sentiment inference and supports scalable data handling, ensuring efficiency and flexibility. The dashboard also includes features such as review comparison, exportable insights, and real-time analysis, making it suitable for both technical and non-technical users. By automating multilingual sentiment analysis, this project reduces the need for manual review analysis and enables organizations to make data-driven decisions quickly and accurately. The solution is particularly beneficial for global e-commerce businesses, market researchers, and customer experience teams seeking to understand customer sentiment across diverse linguistic markets. Overall, the project demonstrates how AI-driven analytics can transform raw textual data into meaningful business intelligence in a multilingual environment. |
| AUTHOR | P MENMATHI, DR.C. DANIEL NESAKUMAR Student, Department of Computer Applications, Sri Ramakrishna College of Arts and Science, Coimbatore, India Assistant Professor, Department of Computer Applications, Sri Ramakrishna College of Arts & Science, Coimbatore, India |
| VOLUME | 181 |
| DOI | DOI: 10.15680/IJIRCCE.2026.1402036 |
| pdf/36_Multilingual Sentiment Analysis for E-Commerce Product Reviews.pdf | |
| KEYWORDS | |
| References | [1] Pang, B. and Lee, L., “Opinion Mining and Sentiment Analysis,” Foundations and Trends in Information Retrieval, vol. 2, no. 1–2, pp. 1–135, 2008. [2] Liu, B., Sentiment Analysis and Opinion Mining, Morgan & Claypool Publishers, 2012. [3] Jurafsky, D. and Martin, J. H., Speech and Language Processing, Pearson Education, 2nd Edition, 2014. [4] Google AI, “Multilingual Natural Language Processing and Language Detection,” Google AI Documentation. |
