An empirical study on detecting fake reviews using machine learning techniques
Bibliographic record
Abstract
Reputation systems in E-commerce (EC) play a substantial role that allows various parties to achieve mutual benefits by establishing relationships. The reputation systems aim at helping consumers in deciding whether to negotiate with a given party. Many factors negatively influence the sight of the customers and the vendors in terms of the reputation system. For instance, lack of honesty or effort in providing the feedback reviews, by which users might create phantom feedback from fake reviews to support their reputation. Moreover, the opinions obtained from users can be classified into positive or negative which can be used by a consumer to select a product. In this paper, we study online movie reviews using Sentiment Analysis (SA) methods in order to detect fake reviews. Text classification and SA methods are applied on a real conducted dataset of movie reviews. Specifically, we compare four supervised machine learning algorithms: Naïve Bayes (NB), Support Vector Machine (SVM), K-Nearest Neighbors (KNN-IBK), and Decision Tree (DT-J48) for sentiment classification of reviews in two different situations without stopwords and with stopwords methods are employed. The measured results show that for both methods the SVM algorithm outperforms other algorithms, and it reaches the highest accuracy not only in text classification but also to detect fake reviews.
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 | 0.007 | 0.045 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.000 |
| Bibliometrics | 0.002 | 0.002 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.001 | 0.002 |
| Open science | 0.001 | 0.000 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.001 | 0.000 |
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".