MétaCan
Menu
Back to cohort

Fake Job Detection using Bi-GRU Algorithms with Combination Random Over Sampler and Weighted Random Sampler

2025· article· W7130687091 on OpenAlexaff
Refael Frances Havergal Sibarani, Rana Zaini Fathiyana, Desi Nurnaningsih

Bibliographic record

Venuenot available
Typearticle
Language
FieldComputer Science
TopicImbalanced Data Classification Techniques
Canadian institutionsArtificial Intelligence in Medicine (Canada)
Fundersnot available
KeywordsRandom forestOversamplingEmbeddingPrecision and recallRecallProcess (computing)Sampling (signal processing)

Abstract

fetched live from OpenAlex

In order to address data imbalance, this study created a model for identifying fraudulent job openings using the Bidirectional Gated Recurrent Unit (Bi-GRU) algorithm in conjunction with Random Over Sampler and Weighted Random Sampler. With 17.880 data points 95.16% actual and 4.84% false. The EMSCAD dataset was utilized, the model integrates numerical features (salary_range) that are standardized using StandarScaler, and text processing with GloVe embedding and attention technique. To address severe class imbalance, a mix of oversampling and weighted sampling approaches was used. This study use the Cross Industry Standard Process for Data Mining (CRISP-DM) method, The Bi-GRU model with ROS + WRS combination performed the best according to the trial results Accuracy 99.2%, Precision 91%, Recall 89.2%, F1-Score 90%, and ROC Curve 0.9909. This model outperforms other studies (Bi-LSTM 98.71%, XGBoost 97.8%, Random Forest 97%, Transformer XLNet model 83.9%), in identifying fraudulent job openings with an ideal balance between Precision and Recall demonstrating the efficacy of hybrid data balancing strategies. This study lowers financial losses from fraud, boosts user confidence in online recruitment platforms and offers a reliable detection method for production deployment.

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 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)0.001
metaresearch head score (Gemma)0.000
Version: codex-gemma-dda1882f352aValidation status: machine_predicted_unvalidated
Candidate categoriesMeta-epidemiology (narrow), Scholarly communication
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Other design · Consensus signal: none
GenreCandidate signal: Methods · Consensus signal: none
Teacher disagreement score0.885
Threshold uncertainty score1.000

Codex and Gemma teacher scores by category

CategoryCodexGemma
Metaresearch0.0010.000
Meta-epidemiology (narrow)0.0010.001
Meta-epidemiology (broad)0.0010.000
Bibliometrics0.0010.002
Science and technology studies0.0010.000
Scholarly communication0.0010.002
Open science0.0010.000
Research integrity0.0000.001
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 head0.021
GPT teacher head0.276
Teacher spread0.255 · 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

Classification

machine, unvalidated

Machine predicted; a candidate call from one teacher head, not a consensus.

Study designOther design
Domainnot available
GenreMethods

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".

Quick stats

Citations0
Published2025
Admission routes1
Has abstractyes

Explore more

Same topicImbalanced Data Classification TechniquesFrench-language works237,207