Bibliographic record
Abstract
Detecting malicious user accounts on Twitter has become an active area of research in social network analysis.This kind of ill-intentioned users send undesired tweets to other users to promote products, services, rumors, fake news, or any abusive content.Hence, the detection of those spammers and their originators will prevent deterioration in the quality of communication services and legitimate users from being affected.Traditional machine learning techniques have been proposed to tackle the problem of spammers detection.However, many researchers have pointed out that the majority of machine learning based models that rely on supervised classification didn't perform well in noisy and short message platforms like Twitter.Recently, deep learning-based alternatives have shown remarkable performance in this area because of their competitive training speed and low implementation cost.In this paper, we propose a new hybrid architecture that combines Principal Component Analysis (PCA) with Convolutional Neural Network (CNN) to give birth to a more reliable and robust model for spammers detection in Twitter.Unlike other hybridizations, the convolutional layer in the CNN module is not fed traditionally by raw feature vectors, rather, we use very low dimensional vectors containing high-order features provided by PCA module.A series of nicely conducted experiments over benchmark datasets have shown that the hybridization proved to be effective for the detection of spammers.The results show that PCA-CNN model can achieve better classification performance with 94.91% precision, 96.76% recall, and 95.83% F-score when compared to baseline benchmarks like CNN, ANN and SVM.
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 imitationNot 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.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.002 | 0.009 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 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 teacher head, 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".