Glaucoma-related posts from a Chinese social media: An exploratory study

Abstract

Abstract Purpose: Our study aims to discuss glaucoma patients' needs and Internet habits using big data analysis and Natural Language Processing (NLP) based on deep learning (DL). We also developed and validated DL models to recognize social media data. Methods: In this retrospective study, we used web crawler technology to crawl glaucoma-related topic posts from the glaucoma bar of Baidu Tieba. According to the contents of topic posts, we classified them into posts with or without seeking medical advice. Word Cloud and frequency statistics were used to analyze the contents and visualize the keywords. Two DL models, Bidirectional Long Short-Term Memory (Bi-LSTM) and Bidirectional Encoder Representations from Transformers (BERT), were trained to identify the posts seeking medical advice. The evaluation matrices included: accuracy, F1 value, and the area under the ROC curve (AUC). Results: A total of 10,892 topic posts were included, among them, most were seeking medical advice (N=7071, 64.91%), and seeking advice regarding symptoms or examination (N=4913, 45.11%) dominated the majority, followed by searching for social support , expressing emotions, and sharing knowledge. The word cloud analysis showed that ocular pressure, visual field, examination, and operation were the most frequent words. The accuracy, F1 score, and AUC were 0.891, 0.891, and 0.931 for BERT model, 0.82, 0.821, and 0.890 for Bi-LSTM model. Conclusion: Social media can help enhance the patient-doctor relationship by providing patients’ concerns and cognition about glaucoma. DL models performed well in classifying Chinese medical-related texts, which could play an important role in public health monitoring.