Hybrid Deep Learning Approach and Word2Vec Feature Expansion for Cyberbullying Detection on Indonesian Twitter
Bibliographic record
Abstract
Twitter, a social media platform that enables users to generate, post, update, and peruse brief messages known as tweets, unfortunately, is frequently misused for circulating negative content encompassing cyberbullying.The detrimental effects of cyberbullying on the mental well-being of victims are profound, with extreme cases culminating in suicide due to severe stress.Consequently, preventive measures, inclusive of the development of a cyberbullying detection system for Twitter, are imperative.This study introduces a hybrid deep learning approach, incorporating feature expansion with Word2Vec and feature extraction with TF-IDF, for constructing a cyberbullying detection system tailored to the Indonesian language on Twitter.A sequence of test scenarios was executed on a system developed using a dataset of 29,085 Indonesian tweets.The outcomes of this study demonstrate that the highest accuracy was achieved by the CNN-LSTM hybrid model with an accuracy of 79.26%, and the LSTM-CNN hybrid model with an accuracy of 79.48%.These findings substantiate that the amalgamation of hybrid models, Word2Vec for feature augmentation, and TF-IDF for feature extraction, yields superior accuracy compared to other deep learning models.Consequently, this study has succeeded in identifying cyberbullying on Twitter, contributing to the development of a healthier social media environment for users.
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 | 0.000 | 0.001 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.001 |
| Open science | 0.000 | 0.001 |
| Research integrity | 0.000 | 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".