Review Spam Detection by Highlighting Potential Spammers and Diminishing Their Effect
Bibliographic record
Abstract
Nowadays, millions of products and services are available to the public online. Therefore, searching for the best products which meets individuals' expectations would be difficult due to the existence of too many alternative choices. One of the most reliable approaches to choose a product or service is to exploit the experience of people who have already tried them, and are expected to have reported their almost honest opinions about them. A reviewing system is a place where individuals share their experience on products and services. Individuals may read and/or write their reviews which may be neutral and professional or biased. Moreover, companies utilize reviewing systems to apply opinion mining techniques in order to improve their goods or services and may be to watch their competitors. However, the popularity of reviewing systems ignites this motivation for some people to try to influence viewers by entering their fake reviews to promote some products or defame some others. These spam reviews should be detected and eliminated to prevent misleading potential customers and unethically affect the market. Opinion mining should be adapted to locate and eliminate potential spam reviews. In this paper, some review spam detection approaches have been proposed and examined over a sample dataset. The proposed approaches consider patterns that existed in trends of reviews, as well as reviewers' behavior. The approaches depend on various strategies such as observing abnormal trends, detecting uncommon or suspicious behaviors, investigating group activities, among others. The reported test results revealed some promising outcome.
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 | 0.003 | 0.014 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.007 | 0.002 |
| Science and technology studies | 0.001 | 0.000 |
| Scholarly communication | 0.002 | 0.002 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.000 |
| Insufficient payload (model declined to judge) | 0.001 | 0.002 |
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".