Explaining and predicting click-baitiness and click-bait virality

Purpose In the age of social media, when publishers are vying for consumer attention, click-baits have become very common. Not only viral websites but also mainstream publishers, such as news channels, use generating traffic. Therefore, click-bait detection and prediction virality important challenges media platforms to keep platform free give a better user experience. The purpose this study is try exploring how contents posts article can be used explain predict click-bait. Design/methodology/approach This has 17,745 tweets from Twitter with 4,370 top 27 applied econometric along machine learning methods click-baitiness virality. Findings finds that language formality, readability, sentiment scores proper noun usage various parts target plays differential roles in Research limitations/implications paper contributes toward literature dark behavior at large explanation particular. It focuses on post, shared source explaining via psycho-linguistic framework. provides explanability predictive models, thus performing methodological contribution too. Practical implications helps managers create mechanism detect which ones them so corrective measures taken. Originality/value To best authors’ knowledge, one first papers focus both predicting