Performance Evaluation for the use of ELMo Word Embedding in Cyberbullying Detection
Bibliographic record
Abstract
Communication using modern internet technologies has revolutionized the ways humans exchange information.. Despite the numerous advantages offered by such technology, its applicability is still limited due to problems stemming from personal attacks and pseudoattacks. On social media platforms, these toxic contents may take the form of texts (e.g., online chats, emails), speech, and even images and movie clips. Because the cyberbullying of an individual via the use of such toxic digital content may have severe consequences, it is essential to design and implement, among others, various techniques to automatically detect, using machine learning approaches, cyberbullying on social media. It is important to use word embedding techniques to represent words for text analysis, typically in the form of a real-valued vector that encodes the meaning of words. The extracted embeddings are used to decide if a digital input contains cyberbullying contents. Supplying strong word representations to classification methods is a key facet of such detection approaches. In this paper, we evaluate the ELMo word embedding against three other word embeddings, namely, TF-IDF, Word2Vec, and BERT, using three basic machine learning models and four deep learning models. The results show that the ELMo word embeddings have the best results when combined with neural network-based machine learning models.
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 | 0.004 | 0.010 |
| Meta-epidemiology (narrow) | 0.003 | 0.000 |
| Meta-epidemiology (broad) | 0.002 | 0.001 |
| Bibliometrics | 0.003 | 0.001 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.001 | 0.002 |
| Open science | 0.001 | 0.002 |
| Research integrity | 0.002 | 0.001 |
| Insufficient payload (model declined to judge) | 0.002 | 0.002 |
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".