Enhancing Fake News Detection via PSO-Optimized Ensemble Learning: A Comparative Study of SVM, NB, and RF
Bibliographic record
Abstract
Given the rapid spread of fake news across digital platforms, there is a pressing need for a reliable and efficient detection method.Current ensemble learning models often lack optimal weight tuning, limiting their performance in fake news classification tasks.To address this gap, we propose a Particle Swarm Optimization (PSO)-optimized ensemble model that integrates Support Vector Machines (SVM), Naive Bayes, and Random Forest (RF) classifiers using a soft voting strategy.Text data is preprocessed and transformed into numerical features using TF-IDF vectorization.The dataset, derived from the ISOT Fake News corpus, is split into training (80%) and testing (20%) subsets.Each base classifier is individually trained and evaluated, followed by the construction and assessment of an unoptimized voting ensemble.Subsequently, PSO is employed to fine-tune the weights of the base classifiers within the voting ensemble, enhancing overall prediction performance.The optimized model achieves 98.32% accuracy and an F1-score of 98.33%, outperforming both the unoptimized ensemble and standalone classifiers, as well as surpassing several state-of-the-art methods.This approach not only improves detection accuracy but also offers a scalable, interpretable, and effective solution to the fake news problem.Performance is evaluated using standard metrics such as ROC curves and confusion matrices, providing a comprehensive assessment of the model's reliability.
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 | 0.007 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.002 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.002 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.000 | 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".