A symptom is the physical indication of an unstable state or the beginning of diseases. Symptom analysis is an essential factor in the medical area, where it is used for disease diagnosis, drug prescription, and the development of new pharmaceuticals. Commensurate with its importance, symptom analysis has been the subject of various studies in recent years. However, prior literature on this topic has been largely limited to studying symptoms for a specific disease. Our paper attempts to expand and build on previous studies by introducing a network-based symptom analysis. Symptom analysis that can provide a basis for analyzing symptoms related to various diseases. For a universal symptom analysis system, we proposed a network-based symptom analysis. In order to construct a symptom network, we utilized Medical Subject Heading (MeSH) terms and the PubMed search engine which are maintained and developed by the National Center for Biotechnology Information (NCBI) at the National Library of Medicine (NLM). We identified symptomdisease relationships with two measurements, the term frequency-inverse document frequency (TF-IDF) and frequent occurrence of two terms (co-occurrence) from PubMed articles. Symptom-symptom pairs, which is the outline for symptom network, were built up based on symptom-disease relationships. As a result, we constructed a symptom network with 223 nodes and 5313 edges. Evaluations were performed in two ways, compared with two symptom clusters and demonstrated with previous researches. Additionally, proposed method has shown possibility for a guideline of clinical demonstration and a discovery of potential symptoms pair.