MétaCan
Menu
Back to cohort

Retraction Notice: Spam Detection for Social Media Networks Using Machine Learning

2022· article· W7150969612 on OpenAlex

Why this work is in the frame

A frame that forgets how it found something cannot be audited. These are the routes that admitted this work.

aboutThe title or abstract carries a Canadian signal from the geographic lexicon.
no affNo Canadian affiliation: this work is invisible to an affiliation-only frame.
No Canadian affiliation. An affiliation-only frame, the usual design, would never have seen this work. It is one of the works that make the case for inverting the frame.

Bibliographic record

Venue2022 8th International Conference on Advanced Computing and Communication Systems (ICACCS) · 2022
Typearticle
Language
FieldComputer Science
TopicSpam and Phishing Detection
Canadian institutionsnot available
Fundersnot available
KeywordsSocial mediaSpambotThe InternetSupport vector machineForum spam

Abstract

fetched live from OpenAlex

People frequently examine internet product reviews before purchasing a product. More merchants aim to deceive users in order to earn a profit. Because customers are misled in this way, it's critical to be aware of and delete fraudulent reviews. This study examines machine learning-based spam detection approaches and discusses their general perspectives and outcomes. Knowing how important customer reviews are to a product's success, marketers frequently try to fool customers by publishing phoney remarks. Merchants have the option of posting updates themselves or hiring others to do so for them. Comment or review spam is the practice of sending out false updates. Spam senders might be recruited to leave favorable or negative reviews that harm competitor business. By 2020, the Canadian Competition Bureau gave a warning to its citizens officially, stating that they should be careful of fraudulent reviews and estimating that one off three of online reviews is fake. Poll fiction taken from more than twenty-five thousand participants by 2020 claims that more than seventy percent of consumers trust online reviews. As a result, spam reviews are a major source of concern nowadays. Based on the goal of the proposed techniques, the majority of the published articles dealing with this subject can be segregated into three. Tactics can be used to get spam reviews, individual spam senders, or spams sent by groups. Because the spam sent in group methods haven't been thoroughly investigated; they aren't discussed in this work. Spam detection is a machine learning issue that requires supervision. This means you'll need to give your machine learning model a set of spam and ham message examples and tell it to look for the relevant patterns that distinguish the two groups. Most email service providers hav

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.

Direct model labels (unvalidated)

Per-model category and study-design labels from the labeling rounds. They are machine output, unvalidated, and the disagreement between models ships as data. No study design here is MEDLINE-validated yet.

Model armCategoriesStudy designConfidence
gemmano category
Domain: not available · Genre: Other
About the Canadian research system: no · About a Canadian topic: no
Not applicablehigh
gptResearch integrity
Domain: not available · Genre: Editorial
About the Canadian research system: no · About a Canadian topic: no
Not applicablehigh
models splitAgreement compares identical category sets and study designs across arms.

Full frame distilled prediction

Teacher imitation

Not 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.

metaresearch head score (Codex)0.003
metaresearch head score (Gemma)0.000
Version: codex-gemma-dda1882f352aValidation status: machine_predicted_unvalidated
Candidate categoriesMeta-epidemiology (narrow), Science and technology studies, Scholarly communication, Research integrity
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Simulation or modeling · Consensus signal: Simulation or modeling
GenreCandidate signal: Empirical · Consensus signal: none
Teacher disagreement score0.906
Threshold uncertainty score1.000

Codex and Gemma teacher scores by category

CategoryCodexGemma
Metaresearch0.0030.000
Meta-epidemiology (narrow)0.0000.001
Meta-epidemiology (broad)0.0010.000
Bibliometrics0.0010.001
Science and technology studies0.0050.000
Scholarly communication0.0010.001
Open science0.0020.001
Research integrity0.0000.003
Insufficient payload (model declined to judge)0.0000.000

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.

Opus teacher head0.077
GPT teacher head0.326
Teacher spread0.249 · how far apart the two teachers sit on this one work
Validation statusscore_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it