Cross-Platform Reputation Generation System Based on Aspect-Based Sentiment Analysis

Abstract

The active growth of Internet-based applications such as social networks and ecommercewebsites leads people to generate
a tremendous amount of opinions and reviews about products and services.Thus, it becomes very crucial to automatically process them. Over the last ten years, many systems have beenproposed to generate and visualize reputation by mining textual and numerical reviews. However, they haveneglected the fact that online reviews could be posted by malicious users that intend to affect the reputation ofthe target product. Besides, these systems provide an overall reputation value toward the entity and disregardgenerating reputation scores toward each aspect of the product. Therefore, we developed a system thatincorporates spam filtering, review
popularity, review posting time, and aspectbased sentiment analysis togenerate accurate and reliable reputation values. The proposed
model computes numerical reputation valuesfor an entity and its aspects based on opinions collected from various platforms. Our proposed system alsooffers an advanced visualization tool that displays detailed information about its output. Experiment resultsconducted on multiple datasets collected from various platforms (Twitter, Facebook, Amazon . . . ) show theefficacy of the proposed system compared with state-ofthe- art reputation generation systems