Bibliographic record
Abstract
ABSTRAK E-mel merupakan antara perkhidmatan komunikasi yang paling popular dewasa ini. Penggunaan e-mel tidak melibatkan kos yang tinggi serta pantas di dalam menyampaikan maklumat. Namun begitu, lambakan e-mel spam banyak menimbulkan masalah kepada pengguna, organisasi dan penyedia servis Internet. E-mel spam menyebabkan produktiviti kerja menurun dan kerugian dari segi penggunaan jalur lebar dan storan. Justeru itu, satu kajian telah dilakukan bagi menapis e-mel spam menggunakan rangkaian neural perambat balik. Data bagi kajian diperolehi dari e-mel peribadi penulis yang dikumpul selama 6 bulan. Perkataan yang wujud pada kandungan e-mel digunakan bagi melatih rangkaian neural. Perkataan terlebih dahulu diekstrak dari e-mel dan melalui pra proses data. Pra proses data melibatkan pembuangan kata henti, cantasan, penjanaan matriks perkataan e-mel dan umpukan pemberat terhadap perkataan. Perlaksanaan cantasan menggunakan algoritma Porter bagi perkataan bahasa Inggeris dan algoritma Fatimah bagi perkataan bahasa Malaysia. Umpukan pemberat bagi perkataan menggunakan TF-IDF dan teknik khi kuasa dua digunakan bagi memilih perkataan yang akan melatih rangkaian neural. Pemberat TF-IDF perkataan akan ditukar ke nilai 0 hingga 1 menggunakan pernormalan minimummaksimum sebelum menjadi input kepada rangkaian neural. Kriteria pemilihan model terbaik adalah berdasarkan kepada ketepatan ramalan set latihan tertinggi bagi rangkaian neural. Hasil eksperimen dibandingkan dengan kajian lepas mendapati gabungan pemberat TF-IDF dan khi kuasa dua memberikan keputusan ramalan yang memuaskan. Katakunci: Pengelasan e-mel spam, pra pemprosesan data, rangkaian neural
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) | 0.000 | 0.000 |
| Bibliometrics | 0.001 | 0.000 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.002 | 0.002 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.105 | 0.030 |
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".