近年來網路上流傳大量衛生教育謠言已為醫療照護人員帶來嚴重困擾，不實謠言除了誤導病患、造成恐慌外，更可能造成錯誤用藥、延誤治療等嚴重後果，更甚者，還可能造成醫病關係惡化，傷害醫師與醫院形象, 因此發展新的闢謠與防範機制成為急需研究的重要議題。關於謠言防範，醫療機構雖提供正確衛教宣導, 但侷於人力與資源不足, 成效有限, 而人工智慧技術快速發展為此問題帶新的解決方向。本計畫擬運用深度學習技術BERT (Bidirectional Encoder Representations from Transformers)發展新一代衛教謠言檢測系統, 主要功能包括衛教謠言評估與提供個人化衛教資訊 (e.g.,藥品、療法、飲食、運動)。研究計畫分為二階段：階段一運用BERT技術建構衛教謠言檢測系統; 階段二運用科技接受模型(Technology Acceptance Model)分析使用者對衛教謠言檢測系統之使用意圖，本計畫成果將有助於緩解不實謠言對病患的影響。 ;The circulation of numerous health care rumors on the internet in recent years has become extremely troublesome for medical and healthcare personnel. False rumors have misled patients, created panic, and even resulted in medication misuse and delayed treatment. They may also cause deteriorating doctor-patient relationships and tarnish the images of doctors and hospitals. Developing new mechanisms to dispel and prevent rumors has thus become an imperative issue in research. Although medical institutions promote accurate health education, limited labor and resources limit their effectiveness. The rapid progress in artificial intelligence technology is offering a new direction to solve this problem. This project aims to apply deep learning technologies, BERT (Bidirectional Encoder Representations from Transformers), to develop a new-generation health care rumor recognition system mainly functioning to assess food and drug rumors and provide personalized health information (e.g., information on medication, therapy, diet, and exercise). This project will be divided into two phases. In Phase 1, we will use artificial intelligence technology to construct a health care rumor recognition system. System design and testing will be based on the prevention and health education. In Phase 2, we will employ the Technology Acceptance Model to examine user intention to use the health care rumor recognition system. The achievements of this project will help to alleviate the impact of false rumors on patients.
