Machine-learning powered email automation to improve author compliance

<p xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" class="first" dir="auto" id="d3609823e73">A scalable email automation system driven by machine learning is presented, designed to streamline editorial workflows by accurately detecting manuscripts that require author revision. Authors are efficiently engaged through automated, customizable email communications. By reducing manual administrative efforts, this approach enables editorial teams to allocate more time to higher-value editorial responsibilities.