MétaCan
Menu
← Back to cohort
Record W4392966345 · doi:10.21203/rs.3.rs-4109962/v1

Detection of Banglish Slang in Social Media Comments Using a Hybrid Bidirectional Long Short-Term Memory (Bi-LSTM) Model

2024· preprint· en· W4392966345 on OpenAlexaff
Osama Ibrahim Khalaf, Suraiya Yasmin, Rashedul Islam Jisan, Muhammad Fiazul Haque, Sameer Algburi, Habib Hamam

Bibliographic record

VenueResearch Square · 2024
Typepreprint
Languageen
FieldComputer Science
TopicNatural Language Processing Techniques
Canadian institutionsUniversité de Moncton
Fundersnot available
KeywordsSlangTerm (time)Long short term memoryComputer scienceSocial mediaArtificial intelligenceSpeech recognitionLinguisticsWorld Wide WebPhilosophyPhysicsRecurrent neural networkArtificial neural network

Abstract

fetched live from OpenAlex

Abstract Banglish slang is a distinctive mashup of Bengali and English terms that is widely used in messaging applications, social media, and other casual contexts. It has grown to be an essential component of Bangladesh's linguistic landscape. The use of Banglish slang in social media comments has become more common among young people from Bangladesh in recent years. Yet, because traditional language processing methods are not appropriate for managing such linguistic complexity, automated text analysis systems find it difficult to handle this informal communication style. Our proposed model captures the unique components of Banglish slang, such as slang phrases, misspellings, and abbreviations, by combining character-level and word-level properties since it is the most common form of communication and improves user interaction and content moderation. We remove special characters from the dataset and transform all test results to lowercase. After then, the stop words are removed from the dataset. Furthermore, we do tokenization using a pad sequence prior to classification. Stack Bidirectional Long Short-Term Memory (Bi-LSTM) model, a neural network architecture used in Natural Language Processing (NLP), is a state-of-the-art model utilized in this research to classify slang in Banglish words. On the training set with an outstanding 99% accuracy and a strong 79.8% validation accuracy, the suggested model beats traditional approaches. The Mendeley dataset was used to analyze social media comments to detect instances of Banglish slang. To carry out the work, approximately five thousand comments are considered overall. The experimental findings show how well our recommended approach works to identify Banglish slang. This method can be useful in monitoring content and language learning, among other real-world applications.

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 imitation

Not 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.

metaresearch head score (Codex)0.000
metaresearch head score (Gemma)0.001
Version: metacan-v3-hybrid-931329e0061cValidation 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: Empirical
Teacher disagreement score0.009
Threshold uncertainty score0.017

Distilled classifier scores by category (both heads)

CategoryCodexGemma
Metaresearch0.0000.001
Meta-epidemiology (narrow)0.0010.000
Meta-epidemiology (broad)0.0000.001
Bibliometrics0.0010.001
Science and technology studies0.0000.000
Scholarly communication0.0010.001
Open science0.0010.001
Research integrity0.0010.001
Insufficient payload (model declined to judge)0.0010.001

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 head0.097
GPT teacher head0.407
Teacher spread0.310 · 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 source (direct Gemma or distilled Codex), 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

Citations0
Published2024
Admission routes1
Has abstractyes

Explore more

Same venueResearch Square→Same topicNatural Language Processing Techniques→French-language works237,207→