Clickbait detection: quick inference with maximum impact
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2026
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866914461436084224 |
|---|---|
| author | Kuntur, Soveatin Ningrum, Panggih Kusuma Wróblewska, Anna Ganzha, Maria Paprzycki, Marcin |
| author_facet | Kuntur, Soveatin Ningrum, Panggih Kusuma Wróblewska, Anna Ganzha, Maria Paprzycki, Marcin |
| contents | We propose a lightweight hybrid approach to clickbait detection that combines OpenAI semantic embeddings with six compact heuristic features capturing stylistic and informational cues. To improve efficiency, embeddings are reduced using PCA and evaluated with XGBoost, GraphSAGE, and GCN classifiers. While the simplified feature design yields slightly lower F1-scores, graph-based models achieve competitive performance with substantially reduced inference time. High ROC--AUC values further indicate strong discrimination capability, supporting reliable detection of clickbait headlines under varying decision thresholds. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2604_08148 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Clickbait detection: quick inference with maximum impact Kuntur, Soveatin Ningrum, Panggih Kusuma Wróblewska, Anna Ganzha, Maria Paprzycki, Marcin Computation and Language We propose a lightweight hybrid approach to clickbait detection that combines OpenAI semantic embeddings with six compact heuristic features capturing stylistic and informational cues. To improve efficiency, embeddings are reduced using PCA and evaluated with XGBoost, GraphSAGE, and GCN classifiers. While the simplified feature design yields slightly lower F1-scores, graph-based models achieve competitive performance with substantially reduced inference time. High ROC--AUC values further indicate strong discrimination capability, supporting reliable detection of clickbait headlines under varying decision thresholds. |
| title | Clickbait detection: quick inference with maximum impact |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2604.08148 |