Fake Review Detection Using Machine Learning
Bibliographic record
Abstract
Online customer reviews have become an increasingly influential tool in shaping purchasing decisions.However, the growing impact of these reviews has led to a surge in the publication and promotion of fake reviews by some businesses, either to enhance their own product's reputation or to undermine their competitors.These counterfeit reviews can have an especially detrimental impact on small businesses, with even a single negative fake review capable of causing significant damage.In this context, the current study introduces a technique for classifying and identifying fake reviews using machine learning (ML) methodologies.The proposed algorithm was applied to the Yelp dataset for hotel services.The text was initially preprocessed through four stages: tokenization, normalization, stop word removal, and stemming.Subsequently, features were extracted using TFIDF techniques to leverage the benefits of sentiment analysis and to ascertain the presence of spam comments in the feature extraction approach.During the classification phase, the study employed three ML algorithms: Xgboost, a support vector classifier, and stochastic gradient descent.The proposed model was evaluated on both balanced and imbalanced datasets, using oversampling and undersampling techniques to determine its accuracy.The findings of this research hold promise for enhancing the credibility of online reviews and protecting businesses from the adverse effects of fake reviews.By unmasking fraudulent reviews, this study contributes to ensuring the integrity of online review platforms and safeguarding the interests of both businesses and consumers.
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 | 0.012 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.004 | 0.002 |
| Science and technology studies | 0.001 | 0.000 |
| Scholarly communication | 0.002 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| 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".