Enhancing Text Based Email Spam Detection Using Attention Based Long Short-Term Memory
Bibliographic record
Abstract
The rise of electronic communication has led to an increased amount of junk emails, thereby making spam a serious cyber security threat. Specifically, in the Indonesian scenario, it is difficult to identify spams due to its nature of containing Indonesian language in an English format, making it easier to evade filters. Conventional Machine Learning Models may find it difficult to identify such trends and may not be flexible enough to adapt to new trends of spams. To overcome this problem, this research proposes the application of text-based spam classifiers designed by applying Long Short-Term Memory with Attention Mechanism. The proposed model was then tested with an Indonesian dataset of 2,617 clean emails, split with an 80-20 ratio of train and testing set. From the experimental findings, it has been seen that by implementing Attention Mechanism in LSTM, one can achieve better accuracy with improved sensitivity and stronger context, with an accuracy of 97.75% and above 97% Precision, Recall, and F1 score respectively, thereby making it more viable and effective with new advances in advanced email security systems.
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) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.000 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.001 | 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".