GEmFakeABSA: graph-embedded fake review detection using aspect-based sentiment analysis
Ganpat Singh Chauhan, Atul Kumar Verma, Shikha Chaudhary, Geetanjali Maurya · 2026
Read GEmFakeABSA: graph-embedded fake review detection using aspect-based sentiment analysis by Ganpat Singh Chauhan, Atul Kumar Verma, Shikha Chaudhary, Geetanjali Maurya (2026) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/PMC13500506.txt.
Description
Ganpat Singh Chauhan and co-authors build in 2026 a detector for fake online product reviews that reads sentiment toward specific product aspects rather than whole texts. Shoppers and manufacturers lean heavily on reviews, which invites fabricated praise or attacks. Their model embeds aspect-based sentiment into a graph neural network that maps how words, aspects, and feelings connect inside a review, exposing pairings that feel unnatural in invented text. The network also encodes links among users, reviews, and products.
Evaluated on 21,034 Amazon reviews spanning 30 product categories, the system reached accuracy in the low ninety percent range in the reported averages. It beat the strongest rival baseline on precision and recall by clear margins. Splits were stratified by product and reviewer to prevent leakage between training and test data, and the authors pitch the tool for real-time moderation duties.
Catalog record
| CREATOR | Ganpat Singh Chauhan, Atul Kumar Verma, Shikha Chaudhary, Geetanjali Maurya |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 156169 |
| LICENSE | https://creativecommons.org/licenses/by/4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |