Overview of HOPE at IberLEF 2024: Approaching Hope Speech Detection in Social Media from Two Perspectives, for Equality, Diversity and Inclusion and as Expectations

Resumen

This paper presents the second edition of the international shared task on multilingual hope speech detection, HOPE 2024, conducted as part of the IberLEF workshop during the SEPLN 2024 conference. This shared task encompassed two distinct subtasks: the detection of hope speech within Equality, Diversity, and Inclusion texts and the identification of hope speech focusing on expectations in two-level, binary, and multiclass classification settings. Nineteen teams participated in the competition, and sixteen submitted their working notes. In the first subtask, the top-ranking team achieved an average Macro F1-score of 71.61. In the second subtask, leading teams demonstrated robust performance with F1 scores exceeding 80.00 for binary classification and 78.00 for multiclass classification settings.