Locality-Sensitive Hashing-Based Link Prediction Process on Smart Campus Education or Online Social Platform

Abstract

With the development of the Internet, smart campus education and online social platforms have become the mainstream of establishing social relationships. Although many users communicate by social networks, the social networks are caught in the problem of relationship sparsity, which severely impedes users’ communication space. More fatally, in the course of building social relationships, the disclosure of sensitive information will cause users’ privacy vulnerable to be compromised by attackers. Therefore, this paper proposes a potential social relationships prediction approach based on locality-sensitive hashing (LSH) to address the above issues. Specifically, the LSH clusters similar users into the same bucket, and the fuzzy computing method is developed to predict the types of social relationships among these similar users. To further alleviate the relationship sparsity problem, the existing social network structure is utilized to predict users’ social relationships and relationship types. Furthermore, the rationality of prediction results is verified by using the social balance theory (SBT). Finally, massive experiments are executed on Epinions, and the experimental results further confirmed the efficiency and accuracy of our methodology in terms of link prediction while guaranteeing privacy-preservation.

Keywords-Driven Paper Recommendation Based on Mobile Edge Computing Environment Framework

“…erefore, more refinements are needed in the future. Second, readers' paper search is often a multiobjective decision-making problem that involves a number of influencing factors [47][48][49][50][51][52][53][54] in the mobile edge computing environment. We will further improve our proposal by considering these factors.…”

Microservice‐driven privacy‐aware cross‐platform social relationship prediction based on sequential information

“…To accurately predict social relationships, some relationship prediction methods overlook users' requirements to prevent disclosure of sensitive information (e.g., age, preference, address, sex, and so on). Currently, some encryption technologies, [37][38][39][40][41][42] for example, anonymity and locality-sensitive hashing (LSH) methods, are studied and applied to protect the users' sensitive information. 43 In Reference 44, the author adopted micro-aggregation technology to implement K-anonymity of data information to protect user privacy, primarily because K-anonymity could partially hide users' sensitive identity information.…”

“…(4) SHLP: 23 Without considering time factors, the SHLP mainly employs the Simhash technique and the social balance theory to build social relationships and relationship types among users. (5) SRP-LSH: 39 Regardless of time factors, the SRP-LSH primarily takes advantage of the users' behavior data and social network structure information to predict social relationships and relationship types between users. Finally, the approach applies the social balance theory to test prediction results.…”

“…To accurately predict social relationships, some relationship prediction methods overlook users' requirements to prevent disclosure of sensitive information (e.g., age, preference, address, sex, and so on). Currently, some encryption technologies, 37‐42 for example, anonymity and locality‐sensitive hashing (LSH) methods, are studied and applied to protect the users' sensitive information 43 …”

“…Note that, the overall relationship prediction model is motivated by the assumption that users who are more similar to each other are more likely to have trust/distrust social relationships. In additionally, how to solve the prediction of the relationship between different users from different buckets by the improved Simhash has been proposed in another of our research works, that is, Reference 39.…”