CoChat
Sign Up
PreprintCited by 3Hate Speech and Cyberbullying DetectionSentiment Analysis and Opinion MiningMental Health via Writing

Cost-sensitive PLM-based Approach for Arabic and English Cyberbullying Classification

Open access
Harbaoui, Azza, Benaissa, Azzeddine Rachid, ghezala, Henda Ben·2023·Research Square
DOI 10.21203/rs.3.rs-2524732/v1
Open this paper in CoChat — free accountOpen PDF

Abstract

Cyberbullying is a hurtful phenomenon that spreads widely on social networks and negatively affects the lives of individuals. Detecting this phenomenon is of utmost necessity to make the digital environment safer for youth. This study uses a bilingual classification of cyberbullying on Ara-bic and English datasets. A four-module approach is proposed. It consists of preprocessing the textual data, generating sentence embeddings, performing the classification, and evaluating the results of the models. The approach relies on two strategies based on transfer learning of pre-trained NLP models. The first uses PLMs (ELMo, Universal Sentence Encoder, BERT, distilBERT, and RoBERTa) to generate sentence embeddings, while the second adopts a fine-tuning procedure of BERT-based PLMs for cyberbullying classification. Due to the frequent class imbalance problem in the research literature, this study used cost-sensitive learning algorithms trained to maximize the Recall/F1 score. The aim is to search for the best classification model that most accurately separates the cyber-bullying and non-cyberbullying classes. The models achieve 75-84%.

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.21203/rs.3.rs-2524732/v1

Cites

49 of 49 references verified0 citation errors · 0 not checkable

Statistics

Claims the paper makes

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Claims other papers make about this one

Each is checked against this paper’s own text: does it say what the citing paper says it does?

  • Several studies used DistilBERT for cyberbullying detection in social networks and obtained promising performance.

    “Several studies [54-56] used DistilBERT for cyberbullying detection in social networks. Their experimental results show that they obtained a promising performance while using DistilBERT as the word-embedding technique as well as the fine-tuned classifier.”

    From A Review on Deep-Learning-Based Cyberbullying Detection (2023) · cites this paper as [54]

    Section 3.3 describes using DistilBERT to generate sentence embeddings, and Section 3.6.2 describes using a fine-tuned DistilBERT model for cyberbullying classification. The Model Performance section reports a cyberbullying-class F1-score of 0.54 for fine-tuned DistilBERT on Formspring, but says Universal Sentence Encoder embeddings were the most effective; it does not establish promising performance for DistilBERT embeddings specifically. The copy provides evidence for this study, not for the other studies grouped with it in the citing sentence; page numbers are unavailable. (LLM, conf=0.78)

    Experimental — accuracy not yet measured

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

The self-check needs the paper’s full text.

Cites

Flagged first, then by citations

3 of the 52 references couldn’t be matched to a known paper.

Research works printed but not linked: 1

  1. Olweus, D.: Bullying at School: What We Know and What We Can Do. Understanding Children's Worlds, Wiley (1993), https://books.google.tn/ books?id=4qNLY13mkDEC

Cited by

Sorted by citations

Related

Authors
Harbaoui, A., Benaissa, A. R., & ghezala, H. B.
Affiliations
  • National School of Computer Science (TN)
  • University of la Manouba
Venue
Research Square
Publisher
Research Square Platform LLC
Published
2023-01-31
DOI
10.21203/rs.3.rs-2524732/v1
OpenAlex
W4318618949
Cited by
3
References
52
Citations by year
2025: 2 · 2023: 1
Type
posted content
Language
en
Open access
Licence
Locations
Research Square (acceptedVersion, cc-by)
Topics
  • Physical Sciences › Computer Science › Artificial Intelligence › Hate Speech and Cyberbullying Detection
  • Physical Sciences › Computer Science › Artificial Intelligence › Sentiment Analysis and Opinion Mining
  • Social Sciences › Psychology › Social Psychology › Mental Health via Writing
Keywords
cyberbullying detection, Arabic text classification, English text classification, pre-trained language models, sentence embeddings, transfer learning, BERT fine-tuning, cost-sensitive learning, class imbalance, social media

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review