Sentilytics: AI-Driven Sentiment Analysis for Amazon Reviews
dc.contributor.author | Ali Abu Nimah | |
dc.contributor.author | Ali Odeh | |
dc.contributor.author | Amr Qamhieh | |
dc.contributor.author | Muawiya Nasser | |
dc.date.accessioned | 2025-02-03T07:28:17Z | |
dc.date.available | 2025-02-03T07:28:17Z | |
dc.date.issued | 2025-02-02 | |
dc.description.abstract | Sentilytics: AI-Driven Sentiment Analysis for Amazon Reviews Sentilytics revolutionizes sentiment analysis by leveraging artificial intelligence to extract meaningful insights from vast volumes of customer reviews on e-commerce platforms like Amazon. The overwhelming number of reviews often makes decision-making difficult for consumers and businesses. To address this, Sentilytics employs the RoBERTa model, an advanced machine learning model, to classify sentiments with high accuracy. The system integrates real-time web scraping for up-to-date reviews, a visually engaging dashboard for trend analysis, and an AI-powered chatbot that summarizes feedback and provides product recommendations. Consumers gain clear insights into sentiment trends, businesses identify strengths and weaknesses, and researchers track market dynamics efficiently. Technologically, Sentilytics utilizes React.js for frontend development, Flask for backend processing, and MongoDB for scalable data storage. Future enhancements include multilingual support, real-time sentiment tracking, and expansion to platforms like eBay and Walmart, ensuring broader global accessibility. By transforming unstructured feedback into actionable intelligence, Sentilytics empowers users with data-driven decision-making, solidifying its role as an essential tool in sentiment analysis and e-commerce research. | |
dc.identifier.uri | https://hdl.handle.net/20.500.11888/19860 | |
dc.language.iso | en | |
dc.supervisor | Dr.Najwam Deleq | |
dc.title | Sentilytics: AI-Driven Sentiment Analysis for Amazon Reviews | |
dc.type | Graduation Project |
Files
License bundle
1 - 1 of 1
Loading...
- Name:
- license.txt
- Size:
- 1.71 KB
- Format:
- Item-specific license agreed upon to submission
- Description: