Fake Review Detection Using Rating-Sentiment Inconsistency
Bibliographic record
Abstract
Fake reviews have been a major problem in online platforms with detrimental effects on customer trust. Different machine learning and natural language processing methods have been used recently to classify fake reviews from authentic ones. Due to the lack of labelled and reliable data in this domain, the right selection of input features plays a critical role in extracting the most useful and relevant information from the review content. This research investigates the impact of inconsistency between a review's rating and its sentiment score in detecting deceptive reviews. Our approach presents two sets of experiments: First with and then without the inclusion of a rating-sentiment inconsistency feature. We use deep learning classifiers and GloVe (Global Vectors for Word Representation), word embeddings to compare the performance of fake review detection models. The results indicate that incorporating the inconsistency feature in the BiGRU (Bidirectional Gated Recurrent Unit) classifier can lead the model to achieve more than 90% accuracy. However, further study is needed to demonstrate its effectiveness since inconsistency also leads to reduction in accuracy for some other models' performance.
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 distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| 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 teacher head, 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".