Optimizing Hate Speech Detection in Indonesian Social Media: An ADASYN and LSTM-Based Approach
Bibliographic record
Abstract
Identifying hate speech in Indonesian social media presents considerable difficulties owing to the intricacies of the language and the varied nature of online material.This paper presents a novel method for improving hate speech identification in Indonesia by tackling the significant class imbalance in Indonesian hate speech datasets.The ADASYN oversampling technique proficiently addresses this problem, representing a notable advancement in this study.The FastText method is utilized for word weighting, improving the prediction efficacy of the classification model.The dataset is carefully curated to authentically reflect the language characteristics and cultural circumstances of Indonesian social media conversation.The long short-term memory (LSTM) method is chosen for its capacity to record long-range relationships in sequential data, essential for comprehending the context of hate speech.The assessment of performance using criteria like accuracy, precision, recall, and F1-Score illustrates the efficacy of this method in precisely detecting hate speech.This research markedly enhances hate speech identification technology in Indonesian language processing, offering a viable method to curtail the dissemination of harmful information on internet platforms.The results of this study include practical implications for formulating more effective tactics to combat hate speech on Indonesian social media.
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 | 0.001 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 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".