2022 Abstract: This paper presents a model of an intelligent distributed support system for pregnant women and mothers with an emphasis on the detection of postpartum depression. There are psychological tests that can be used to determine the degree of postpartum depression, but it is very important to detect the existence of this depression in women who are not aware of it. A lot of women use social networks to share information about their problems. Using tools for natural language processing and machine learning, social network posts that describing problems similar to postpartum depression can be detected. The presented system was tested on a data set of posts from two social media forums (one Serbian and one English). It has been shown that posts indicating postpartum depression can be labeled with an accuracy of up to 89%. This system aims to identify the potential existence of problems and refer to the system for detection and professional assistance. It can contribute to improving the lives of mothers and thus babies. eng https://phaidrabg.bg.ac.rs/o:35326 doi:10.1007/978-3-030-96627-0_34 ISBN: 978-3-030-96626-3 Detection of Postpartum Depression-Related Posts: An Analysis for Serbian. application/pdf 328842 bytes Intelligent Distributed Computing XIV startpage: 377 endpage: 383 info:eu-repo/semantics/article All rights reserved Keywords: Social media, Postpartum depression, Machine learning, natural language processing Marovac, Ulfeta Avdić, Aldina