User Identification Based on Integrating Multiple User Information across Online Social Networks

Abstract

User identification can help us build more comprehensive user information. It has been attracting much attention from academia. Most of the existing works are profile-based user identification and relationship-based user identification. Due to user privacy settings and social network restrictions on user data crawl, user data may be missing or incomplete in real social networks. User data include profiles, user-generated contents (UGCs), and relationships. The features extracted in previous research may be sparse. In order to reduce the impact of the above problems on user identification, we propose a multiple user information user identification framework (MUIUI). Firstly, we develop multiprocess crawlers to obtain the user data from two popular social networks, Twitter and Facebook. Secondly, we use named entity recognition and entity linking to obtain and integrate locations and organizations from profiles and UGCs. We also extract URLs from profiles and UGCs. We apply the locations jointly with the relationships and develop several algorithms to measure the similarity of the display name, all locations, all organizations, location in profile, all URLs, following organizations, and user ID, respectively. Afterward, we propose a fusion classifier machine learning-based user identification method. The results show that the F1 score of MUIUI reaches 86.46% on the dataset. It proves that MUIUI can reduce the impact of user data that are missing or incomplete.

Multi-grained alignment method based on stable topics in cross-social networks

“…Similar user names ( Yuan et al, 2021 ) and user profiles such as profile, education, unit, etc . ( Zeng et al, 2021 ) are important representations of users’ characteristics. Therefore, based on the document similarity algorithm ( Kusner et al, 2015 ), this article employs the combination of user name similarity and personal data similarity to treat users and score matched users.…”

“…User alignment is based on user attributes, behaviors, and topology information. Zeng et al (2021) was matched based on the user’s profile (user name, age, profile, educational background), UGC, and location attributes by plugging them into the fusion classifier of machine learning. In Yuan et al (2021) , the researchers used the backpropagation (BP) neural network to calculate the similarity of the user name by vector mapping.…”

A Semantic-Enhancement-Based Social Network User-Alignment Algorithm

“…There is complementarity or redundancy between these two different types of data. Notably, while a single method with a single type of data cannot deeply mine the semantics of users, hybrid methods that combine user features and network topologies can more fully mine the semantic features of users and thereby improve user alignment [9,[12][13][14]22,[41][42][43][44]. Graph neural networks are commonly used at present to fuse user features and network topologies simultaneously.…”

“…Users' writing patterns, personal emotion, and other semantic features can be mined through an analysis of usernames and text posts [11]. Integrated consideration of the username, user-generated content, geographic location, network topology, and other data can help mine users' semantic features, comprehensively characterize users, and reduce the negative impacts of local feature differences on user-alignment effects [12][13][14][15]. Notably, however, user feature mining methods discussed above do not consider the reliability of data, computing overhead, and missing data problems.…”

A New Joint Approach with Temporal and Profile Information for Social Bot Detection

“…However, social bots can evade detection by constructing enough links with each other. On the other hand, it is difficult to obtain all the relationships of users due to the OSN restrictions [43], which have been a major factor limiting the further development of the approaches.…”