Performance Evaluation of Transformer-based NLP Models on Fake News Detection Datasets
Bibliographic record
Abstract
Fake news has the potential to have catastrophic effects because it is increasingly concerning how it spreads on social media.To identify fake news, various machine learning (ML) techniques have been proposed in recent times.Due to the lack of available research on the performance of various transformer models using datasets that contain data samples from a wide variety of domains, it is essential to increase the research in this field.Hence, this research investigates the performance of various suitable machine learning algorithms implementations on three fake news datasets: LIAR, FNC-1 and Balanced Dataset for Fake News Analysis.Some pre-trained transformer language models, BERT, RoBERTa, ALBERT and DistilBERT, were chosen for this research.The performance of the models utilized in the experiments was consistent across all datasets of varying sizes.The results from the experiments conducted indicated that RoBERTa is the best performing model across all datasets.The results also indicated that DistilBERT trains in half the time required by the other three models.RoBERTa obtained an accuracy of 69% when trained on the LIAR dataset.DistilBERT trained a single epoch within 3.5 minutes, which is significantly faster than what time the other three variants needed to train, 7 minutes.The performance evaluation and the analysis obtained from the results help the research community to advance the investigation and explore insights on fake news detection.i
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 | 0.013 |
| Meta-epidemiology (narrow) | 0.002 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.002 | 0.002 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.002 | 0.003 |
| Open science | 0.002 | 0.001 |
| Research integrity | 0.002 | 0.003 |
| Insufficient payload (model declined to judge) | 0.002 | 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".