In this paper, we present the main findings and compare the results of\nSemEval-2020 Task 10, Emphasis Selection for Written Text in Visual Media. The\ngoal of this shared task is to design automatic methods for emphasis selection,\ni.e. choosing candidates for emphasis in textual content to enable automated\ndesign assistance in authoring. The main focus is on short text instances for\nsocial media, with a variety of examples, from social media posts to\ninspirational quotes. Participants were asked to model emphasis using plain\ntext with no additional context from the user or other design considerations.\nSemEval-2020 Emphasis Selection shared task attracted 197 participants in the\nearly phase and a total of 31 teams made submissions to this task. The\nhighest-ranked submission achieved 0.823 Matchm score. The analysis of systems\nsubmitted to the task indicates that BERT and RoBERTa were the most common\nchoice of pre-trained models used, and part of speech tag (POS) was the most\nuseful feature. Full results can be found on the task's website.\n