MétaCan
Menu
Back to cohort
Record W4312725824 · doi:10.1109/ojcs.2022.3213791

An Attention-Based Neural Network Using Human Semantic Knowledge and Its Application to Clickbait Detection

2022· article· en· W4312725824 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.

affAt least one author lists a Canadian institution in the pinned OpenAlex snapshot.
fundA Canadian funder is recorded on the work.

Bibliographic record

VenueIEEE Open Journal of the Computer Society · 2022
Typearticle
Languageen
FieldSocial Sciences
TopicMisinformation and Its Impacts
Canadian institutionsYork University
FundersNatural Sciences and Engineering Research Council of Canada
KeywordsComputer scienceTask (project management)Artificial intelligencePhishingArtificial neural networkDomain knowledgeDomain (mathematical analysis)DisinformationMachine learningSocial mediaNatural language processingThe InternetWorld Wide Web

Abstract

fetched live from OpenAlex

Clickbait is a commonly used social engineering technique to carry out phishing attacks, illegitimate marketing, and dissemination of disinformation. As a result, clickbait detection has become a popular research topic in recent years due to the prevalence of clickbait on the web and social media. In this article, we propose a novel attention-based neural network for the task of clickbait detection. To the best of our knowledge, our work is the first that incorporates human semantic knowledge into an artificial neural network, and uses linguistic knowledge graphs to guide attention mechanisms for the clickbait detection task. Extensive experimental results show that the proposed model outperforms existing state-of-the-art clickbait classifiers, even when training data is limited. The proposed model also performs better or comparably to powerful pre-trained models, namely, BERT, RoBERTa, and XLNet, while being much more lightweight. Furthermore, we conducted experiments to demonstrate that the use of human semantic knowledge can significantly enhance the performance of pre-trained models in the semi-supervised domain such as BERT, RoBERTa, and XLNet.

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)0.002
metaresearch head score (Gemma)0.000
Version: codex-gemma-dda1882f352aValidation status: machine_predicted_unvalidated
Candidate categoriesScience and technology studies
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Simulation or modeling · Consensus signal: Simulation or modeling
GenreCandidate signal: Empirical · Consensus signal: Empirical
Teacher disagreement score0.166
Threshold uncertainty score0.999

Codex and Gemma teacher scores by category

CategoryCodexGemma
Metaresearch0.0020.000
Meta-epidemiology (narrow)0.0000.000
Meta-epidemiology (broad)0.0000.000
Bibliometrics0.0000.000
Science and technology studies0.0020.000
Scholarly communication0.0000.000
Open science0.0010.000
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 head0.051
GPT teacher head0.361
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