Social network services for self-media, such as Weibo, Blog, and WeChat Public, constitute a powerful medium that allows users to publish posts every day. Due to insufficient information transparency, malicious marketing of the Internet from self-media posts imposes potential harm on society. Therefore, it is necessary to identify news with marketing intentions for life. We follow the idea of text classification to identify marketing intentions. Although there are some current methods to address intention detection, the challenge is how the feature extraction of text reflects semantic information and how to improve the time complexity and space complexity of the recognition model. To this end, this paper proposes a machine learning method to identify marketing intentions from large-scale We-Media data. First, the proposed Latent Semantic Analysis (LSI)-Word2vec model can reflect the semantic features. Second, the decision tree model is simplified by decision tree pruning to save computing resources and reduce the time complexity. Finally, this paper examines the effects of classifier associations and uses the optimal configuration to help people efficiently identify marketing intention. Finally, the detailed experimental evaluation on several metrics shows that our approaches are effective and efficient. The F1 value can be increased by about 5%, and the running time is increased by 20%, which prove that the newly-proposed method can effectively improve the accuracy of marketing news recognition.

Today, wireless sensor networks (WSNs) in electronic engineering are used in the monitoring of remote intelligent buildings, and the need for emerging Web 3.0 is becoming more and more in every aspect of electronic engineering. However, the key challenges of monitoring are the monitoring approaches and storage models of huge historical monitoring data. To address these limitations, we attempt to design a WebSocket-based real-time monitoring system for remote intelligent buildings. On one hand, we utilize the latest HTML5 WebSocket, Canvas and Chart technologies to monitor the sensor data collected in WSNs in the Web browser. The proposed monitoring system supports the latest HTML5 browsers and legacy browsers without native WebSocket capability transparently. On the other hand, we propose a storage model with lifecycle to optimize the NoSQL data warehouse. Finally, we have made the monitoring and storage experiments to illustrate the superiority of our approach. The monitoring experimental results show that the average latency time of our WebSocket monitoring is generally lower than polling, FlashSocket, and Socket solution, and the storage experimental results show that our storage model has low redundancy rate, storage space, and latency.