Summary
Because mobile terminals have limited computing and storage resources, individuals tend to outsource their data generated from mobile devices to clouds to do data operations. However, utilization of the abundant computation and storage resources of clouds may pose a threat to user's private data. In this paper, we focus on the issue of encrypted k‐nearest neighbor (kNN) classification on the cloud. In the past few years, many solutions were proposed to protect the user's privacy and data security. Unfortunately, most privacy‐preserving data mining schemes are not lightweight, which are not practical in real‐world applications. To solve this issue, we proposed a lightweight edge‐based kNN (EBkNN) classification scheme over encrypted cloud database utilizing edge computing technology. Our proposed scheme can provide several security guarantees: (i) user's data security, (ii) user's query privacy, and (iii) data access patterns. We analyzed the security of our scheme utilizing the semi‐honest security model and evaluated the performance using a synthetic dataset. The experiment results indicate that our scheme is more lightweight than the state‐of‐the‐art scheme.
With the rapid development of the Internet, e-commerce and social media have continued to develop and grow. Merchants tend to better understand users’ attitudes and emotional tendencies through comments. As the number of user reviews increases, the previous sentiment analysis methods have highlighted the problems of high cost and high error rate. How to use more advanced methods to analyse comments has become an urgent problem to be solved. In order to solve the above problems, in this article, we propose a fine-grained sentiment analysis method based on dependency tree and graph neural network, which can help businesses and social network platforms to identify users’ sentiment tendencies and can be subsequently used in recommendation systems and public opinion analysis systems. The experimental results show that our scheme has achieved the best results.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.