MétaCan
Menu
Back to cohort
Record W4389493777 · doi:10.31577/cai_2023_4_993

Deep Learning Based Misogynistic Bangla Text Identification from Social Media

2023· article· en· W4389493777 on OpenAlexaff
Sonam Jahan, Raqeebir Rab, Peom Dutta, Hossain Muhammad Mahdi Hassan Khan, Muhammad Shahariar Karim Badhon, Sumaiya Binte Hassan, Ashikur Rahman

Bibliographic record

VenueComputing and Informatics · 2023
Typearticle
Languageen
FieldComputer Science
TopicHate Speech and Cyberbullying Detection
Canadian institutionsUniversity of British Columbia
Fundersnot available
KeywordsBengaliHatredSocial mediaArtificial intelligenceComputer scienceIdentification (biology)Deep learningConfusion matrixHostilityIntimidationMachine learningNatural language processingPsychologyWorld Wide WebSocial psychologyPolitical science

Abstract

fetched live from OpenAlex

Misogyny is characterized by hostility, hatred, aversion, intimidation, and violence against women. With the rise of social media, it has become one of the most convenient platforms for expressing woman-hating speech. As a result, misogyny is gaining appeal and societal standards are being violated. With millions of Bangladeshi Facebook users, misogyny is growing increasingly prevalent in Bangla as well. In this paper, we have proposed automatically identifying misogynistic content in Bangla on social media platforms in order to evaluate the problem's challenges. As there is no existing Bangla dataset for analyzing misogynistic text, we generated our own. We have applied various deep-learning algorithms to improve the classification of misogynistic text categories. LSTM and RNN models are used for designing the model architecture in deep learning. Models are evaluated using the confusion matrix, accuracy, and f1-scores. The results indicate that LSTM outperforms RNN in terms of accuracy by 67 %.

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 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)0.000
metaresearch head score (Gemma)0.000
Version: codex-gemma-dda1882f352aValidation status: machine_predicted_unvalidated
Candidate categoriesnone
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Simulation or modeling · Consensus signal: none
GenreCandidate signal: Empirical · Consensus signal: none
Teacher disagreement score0.966
Threshold uncertainty score0.394

Codex and Gemma teacher scores by category

CategoryCodexGemma
Metaresearch0.0000.000
Meta-epidemiology (narrow)0.0000.000
Meta-epidemiology (broad)0.0000.000
Bibliometrics0.0000.000
Science and technology studies0.0000.000
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 head0.014
GPT teacher head0.232
Teacher spread0.218 · 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

Classification

machine, unvalidated

Machine predicted; a candidate call from one teacher head, not a consensus.

The models applied no category: nothing in the taxonomy fit this work.
Study designSimulation or modeling
Domainnot available
GenreEmpirical

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".

Quick stats

Citations6
Published2023
Admission routes1
Has abstractyes

Explore more

Same venueComputing and InformaticsSame topicHate Speech and Cyberbullying DetectionFrench-language works237,207