Online Health Monitoring and Demand Analysis System Based on Big Data Mining

With the continuous progress of big data technology, the dissemination and access to online health information has become more and more convenient. However, how to effectively monitor and analyse this massive amount of health information to meet the public’s health needs has become an important issue in the field of health communication at present. In this study, an online health monitoring and demand analysis system is developed based on a computational communication approach through text mining techniques. Firstly, text data from a variety of online health information sources, which include health news, forum discussions, and social media comments, are collected. Secondly, Jieba participle is applied to pre-process these text data, including steps such as participle and de-duplication, in order to improve the efficiency and accuracy of data processing. Then, LDA (Latent Dirichlet Allocation) topic model was used to perform topic modelling on the preprocessed text data to identify potential health topics and topic distribution in the data. Finally, the trend of the theme is monitored through methods such as time series analysis to reveal the dynamics of public health needs. The system response time was short, with little overall fluctuation, showing that the system was able to respond quickly to user query requests. Especially on day 4, the response time dropped to 0.30 seconds. This study not only enriches the research methods and application scenarios in the field of health communication, but also provides new perspectives and technical paths for future online health monitoring and demand analysis.