Click it or Leave it: Detecting and Spoiling Clickbait with Informativeness Measures and Large Language Models
This work addresses clickbait detection to improve online information quality and user trust, representing an incremental advance in the field.
The paper tackled the problem of clickbait detection by developing a hybrid approach that combines transformer-based embeddings with linguistically motivated features, achieving an F1-score of 91% and outperforming various baselines.
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.