A Novel Hybrid CNN-LSTM Framework with Ant Colony Optimization for Robust Fake News Detection
Bibliographic record
Abstract
In the digital age, the spread of fake news has become ubiquitous: it weakens public speech and weakens public trust. In this paper we propose a novel method of detecting fake news using a deep learning framework. To do text analysis, we propose a hybrid model that incorporates Convolutional Neural Network and Long Short-Term Memory Network by utilizing on the strengths of each for effective text analysis. However, the LSTM layer is good in learning the context and sequence of the text, and the CNN component beats in extracting local and spatial details in textual data. The effectiveness of the proposed work is tested on a comprehensive data set of news sources (covering different sources, from different countries, and labeled for authenticity). We trained and evaluated the model on this dataset which mainly included features of linguistic and semantic nature to differentiate between genuine and fake news. We show that our results exhibit the biggest accuracy, precision, recall, and Fl-score improvement over old models. Automated fake news detection is a growing field, and this research proposes a robust and scalable solution to cut off the spread of misinformation.
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 | 0.001 | 0.001 |
| Meta-epidemiology (narrow) | 0.002 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.002 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.002 | 0.001 |
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".