Click it or Leave it: Detecting and Spoiling Clickbait with Informativeness Measures and Large Language Models
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_ | 1866918347616026624 |
|---|---|
| author | Michaluk, Wojciech Urban, Tymoteusz Kubita, Mateusz Kuntur, Soveatin Wroblewska, Anna |
| author_facet | Michaluk, Wojciech Urban, Tymoteusz Kubita, Mateusz Kuntur, Soveatin Wroblewska, Anna |
| contents | Clickbait headlines degrade the quality of online information and undermine user trust. We present a hybrid approach to clickbait detection that combines transformer-based text embeddings with linguistically motivated informativeness features. Using natural language processing techniques, we evaluate classical vectorizers, word embedding baselines, and large language model embeddings paired with tree-based classifiers. Our best-performing model, XGBoost over embeddings augmented with 15 explicit features, achieves an F1-score of 91\%, outperforming TF-IDF, Word2Vec, GloVe, LLM prompt based classification, and feature-only baselines. The proposed feature set enhances interpretability by highlighting salient linguistic cues such as second-person pronouns, superlatives, numerals, and attention-oriented punctuation, enabling transparent and well-calibrated clickbait predictions. We release code and trained models to support reproducible research. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2602_18171 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Click it or Leave it: Detecting and Spoiling Clickbait with Informativeness Measures and Large Language Models Michaluk, Wojciech Urban, Tymoteusz Kubita, Mateusz Kuntur, Soveatin Wroblewska, Anna Computation and Language Artificial Intelligence Clickbait headlines degrade the quality of online information and undermine user trust. We present a hybrid approach to clickbait detection that combines transformer-based text embeddings with linguistically motivated informativeness features. Using natural language processing techniques, we evaluate classical vectorizers, word embedding baselines, and large language model embeddings paired with tree-based classifiers. Our best-performing model, XGBoost over embeddings augmented with 15 explicit features, achieves an F1-score of 91\%, outperforming TF-IDF, Word2Vec, GloVe, LLM prompt based classification, and feature-only baselines. The proposed feature set enhances interpretability by highlighting salient linguistic cues such as second-person pronouns, superlatives, numerals, and attention-oriented punctuation, enabling transparent and well-calibrated clickbait predictions. We release code and trained models to support reproducible research. |
| title | Click it or Leave it: Detecting and Spoiling Clickbait with Informativeness Measures and Large Language Models |
| topic | Computation and Language Artificial Intelligence |
| url | https://arxiv.org/abs/2602.18171 |