MétaCan
Menu
Back to cohort
Record W4386810309 · doi:10.18280/ria.370413

Enhancing Cyberbullying Detection on Indonesian Twitter: Leveraging FastText for Feature Expansion and Hybrid Approach Applying CNN and BiLSTM

2023· article· en· W4386810309 on OpenAlex

Why this work is in the frame

A frame that forgets how it found something cannot be audited. These are the routes that admitted this work.

venuePublished in a venue whose home country is Canada.
no affNo Canadian affiliation: this work is invisible to an affiliation-only frame.
No Canadian affiliation. An affiliation-only frame, the usual design, would never have seen this work. It is one of the works that make the case for inverting the frame.

Bibliographic record

VenueRevue d intelligence artificielle · 2023
Typearticle
Languageen
FieldComputer Science
TopicHate Speech and Cyberbullying Detection
Canadian institutionsnot available
Fundersnot available
KeywordsIndonesianFeature (linguistics)Computer scienceArtificial intelligencePattern recognition (psychology)

Abstract

fetched live from OpenAlex

Cyberbullying, characterized by the transmission of threatening, intimidating, and derogatory messages via digital platforms such as Twitter, is a pervasive issue.Given the volume of approximately 867 million daily tweets, the potential scale of cyberbullying incidents is immense, underscoring the necessity for automated detection systems for such messages.However, the context-sensitive nature of tweets can pose challenges to understanding message content, particularly in languages like Indonesian with potential for significant vocabulary discrepancies.This study aims to enhance cyberbullying detection by employing feature expansion using FastText, thereby addressing vocabulary-related comprehension issues in Indonesian-language tweets.Furthermore, text classification is performed using a Hybrid Deep Learning approach, integrating Convolutional Neural Networks (CNN) and Bidirectional Long Short-Term Memory (BiLSTM).This hybrid model leverages the strengths of both techniques, capturing local patterns and long-range dependencies within the data.The objective of this research is to evaluate the performance yielded by the application of FastText-enhanced feature expansion and Hybrid Deep Learning to an Indonesian Twitter dataset.This focus is motivated by the high accuracy of Hybrid Deep Learning for Twitter datasets in other languages, and the limited application of such methods to Indonesian-language datasets, which predominantly use supervised learning or deep learning.Analysis of 29,085 datasets demonstrated that the combined implementation of Hybrid Deep Learning and FastText-enhanced feature expansion achieved the highest accuracy, with CNN-BiLSTM and BiLSTM-CNN scoring 80.55% and 80.35% respectively.These findings validate the significant accuracy boost provided by FastText when integrated with Hybrid Deep Learning.It is anticipated that the outcomes of this study will facilitate the accurate identification and removal of cyberbullying tweets, thereby contributing to a safer digital communication environment on Twitter.

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.

Full frame distilled prediction

Teacher imitation

Not 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.

metaresearch head score (Codex)0.001
metaresearch head score (Gemma)0.000
Version: codex-gemma-dda1882f352aValidation status: machine_predicted_unvalidated
Candidate categoriesMeta-epidemiology (narrow)
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Other design · Consensus signal: none
GenreCandidate signal: Empirical · Consensus signal: none
Teacher disagreement score0.834
Threshold uncertainty score1.000

Codex and Gemma teacher scores by category

CategoryCodexGemma
Metaresearch0.0010.000
Meta-epidemiology (narrow)0.0000.000
Meta-epidemiology (broad)0.0000.000
Bibliometrics0.0000.001
Science and technology studies0.0010.000
Scholarly communication0.0000.000
Open science0.0000.000
Research integrity0.0000.000
Insufficient payload (model declined to judge)0.0000.000

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.

Opus teacher head0.033
GPT teacher head0.252
Teacher spread0.219 · how far apart the two teachers sit on this one work
Validation statusscore_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it