A dual-phase framework for detecting authentic and computer-generated customer reviews using large language models
Bibliographic record
Abstract
Customer reviews are crucial in potential buyers’ decision-making process. However, on online platforms, the credibility of these reviews is often undermined by fake reviews, which can mislead users. With advancements in large language models (LLMs), the review landscape has transformed, making it more common to encounter computer-generated reviews created using state-of-the-art language models rather than genuine user feedback. This evolution poses significant challenges in distinguishing authentic reviews from artificially generated ones. To address these challenges, we propose a novel dual-phase framework that first generates high-diversity synthetic reviews using advanced LLMs to learn their patterns, and then it leverages this knowledge to enhance fake reviews detection. Our methodology involves two key phases. In the first phase, we generate computer-generated reviews by leveraging advanced methods, including generative transformers, trained on genuine user reviews. In the second phase; traditional and deep learning based classifiers, are incorporated as detection models which classify reviews as either authentic or computer-generated. Evaluated on a benchmark Amazon review dataset, our framework demonstrate (1) the efficacy of our approach in generating diverse and contextually relevant human-based and computerized-based reviews and (2) the robustness of our system in classifying and verifying the authenticity of reviews. • Propose a novel end-to-end framework for detecting fake and genuine reviews. • Use modern large language models, including Generative Transformers, for review generation. • Employ traditional and modern classifiers for detection and classification. • Create high-diversity computer-generated reviews for experimental analysis. • Demonstrate strong performance in verifying review authenticity.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.002 | 0.008 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.002 | 0.001 |
| Science and technology studies | 0.000 | 0.001 |
| Scholarly communication | 0.002 | 0.002 |
| Open science | 0.002 | 0.001 |
| Research integrity | 0.001 | 0.002 |
| Insufficient payload (model declined to judge) | 0.001 | 0.001 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".