Leveraging relevant summarized information and multi-layer classification to generalize the detection of misleading headlines

Robiert Sepúlveda-Torres, Marta Esther Vicente, Estela Saquete, Elena Lloret, Manuel Palomar

Abstract: Highlights•HeadlineStanceChecker+ is an enhanced system for misleading headlines detection.•Misleading headlines detection is tackled as a stance detection problem.•Summarization supports stance detection by only selecting relevant information.•A hierarchical classifier effectively determines the stance of a headline.•Results show that extractive approaches perform better for stance detection task.