Search for: All records

Introduction:Detecting water contamination in community housing is crucial for protecting public health. Early detection enables timely action to prevent waterborne diseases and ensures equitable access to safe drinking water. Traditional methods recommended by the Environmental Protection Agency (EPA) rely on collecting water samples and conducting lab tests, which can be both time-consuming and costly. Methods:To address these limitations, this study introduces a Graph Attention Network (GAT) to predict lead contamination in drinking water. The GAT model leverages publicly available municipal records and housing information to model interactions between homes and identify contamination patterns. Each house is represented as a node, and relationships between nodes are analyzed to provide a clearer understanding of contamination risks within the community. Results:Using data from Flint, Michigan, the model demonstrated higher performance compared to traditional methods. Specifically, the GAT achieved an accuracy of 0.80, precision of 0.71, and recall of 0.93, outperforming XGBoost, a classical machine learning algorithm, which had an accuracy of 0.70, precision of 0.66, and recall of 0.67. Discussion:In addition to its predictive capabilities, the GAT model identifies key factors contributing to lead contamination, enabling more precise targeting of at-risk areas. This approach offers a practical tool for policymakers and public health officials to assess and mitigate contamination risks, ultimately improving community health and safety. 

Social networking websites with microblogging functionality, such as Twitter or Sina Weibo, have emerged as popular platforms for discovering real-time information on the Web. Like most Internet services, these websites have become the targets of spam campaigns, which contaminate Web contents and damage user experiences. Spam campaigns have become a great threat to social network services. In this paper, we investigate crowd-retweeting spam in Sina Weibo, the counterpart of Twitter in China. We carefully analyze the characteristics of crowd-retweeting spammers in terms of their profile features, social relationships and retweeting behaviors. We find that although these spammers are likely to connect more closely than legitimate users, the underlying social connections of crowd-retweeting campaigns are different from those of other existing spam campaigns because of the unique features of retweets that are spread in a cascade. Based on these findings, we propose retweeting-aware link-based ranking algorithms to infer more suspicious accounts by using identified spammers as seeds. Our evaluation results show that our algorithms are more effective than other link-based strategies.