Identifying postpartum depression symptoms on social media using machine learning techniques

Postpartum depression (PPD) is one of the most common maternal morbidities following delivery. Most new mothers are at risk of PPD not only after giving birth but also during pregnancy. There is no single cause of PPD, but physical changes, emotional distress, and genetics may play a key role in this issue. The symptoms of PPD can be strong negative feelings faced by mothers, such as never-ending anxiety, sadness, tiredness, mood swings, and more. In this work, we proposed a framework for identifying PPD symptoms based on linguistic features in their textual posts on social media. Nowadays, most people are active on social media platforms to keep in touch with family and friends. Social media allows users to have conversations and share information and feelings through the posting feature that is available on the platform. Thus, this has opened up an opportunity to explore social media’s text content posted by PPD sufferers. We crawled the data using the Twitter (currently known as X) API and preprocessed it to remove noise. In the experiment, Support Vector Machine (SVM) presented the highest accuracy of 87.5% compared to other algorithms. The results indicate that we can utilize the extracted model to gain a deeper understanding of this group.