Intervention algorithm for malicious information in online social networks based on trusted regulator

Trust can be employed for finding reliable information in Online Social Networks (OSNs). Since users in OSNs may intentionally change their behavior over time (in some cases for deceiving other users), modeling (pair-wise) trust relations in such complex environment is a challenging task. However, most of the existing trust prediction approaches assume that trust relations are fixed over time and they fail to capture the dynamic behavior of users in OSNs. In this paper, we propose a dynamic deep trust prediction model. As the impact of incidental emotions on trust has been proven in psychology studies, in this paper, we also study this impact on our trust prediction approach. First, we propose a novel deep structure that incorporates users' emotions and their textual contents in OSNs. Second, we use embeddings to represent the users and their self-descriptions provided. Finally, considering different time windows, we dynamically predict pair-wise trust relations. To evaluate our approach, we collected a large twitter dataset. The evaluation results demonstrate the effectiveness of our approach compared to the state-of-the-art approaches.

The wide availability of online social networks (OSNs) facilitates positive information spread and sharing. However, the high autonomy and openness of the OSNs also allow for the rapid spread of negative information, such as unsubstantiated rumors and other forms of misinformation that often elicit widespread public cognitive misleads and huge economic losses. Therefore, how to effectively control the negative information spread accompanied by positive information has emerged as a challenging issue. Unfortunately, this issue still remains largely unexplored to date. To fill this gap, we propose an efficient feedback control mechanism for the simultaneous spread of the positive and negative information in OSNs. Specifically, a novel computational model is first proposed to present the temporal dynamics of the positive and negative information spread. Furthermore, the proposed mechanism restrains the negative information spread with minimal system expenses by devising and performing three synergetic intervention strategies. Technically, this mechanism intensively evaluates the number of seed users performing three intervention strategies. Besides, each seed user performs the received control task independently, and then the control plan for the next time step is adjusted dynamically according to the previous feedback results. Finally, we evaluate the efficiency of the proposed mechanism based on the extensive experimental results obtained from two real-world networks.

In recent years, due to the booming development of online social networks, fake news for various commercial and political purposes has been appearing in large numbers and widespread in the online world. With deceptive words, online social network users can get infected by these online fake news easily, which has brought about tremendous effects on the offline society already. An important goal in improving the trustworthiness of information in online social networks is to identify the fake news timely. This paper aims at investigating the principles, methodologies and algorithms for detecting fake news articles, creators and subjects from online social networks and evaluating the corresponding performance. This paper addresses the challenges introduced by the unknown characteristics of fake news and diverse connections among news articles, creators and subjects. This paper introduces a novel gated graph neural network, namely FAKEDETECTOR. Based on a set of explicit and latent features extracted from the textual information, FAKEDETECTOR builds a deep diffusive network model to learn the representations of news articles, creators and subjects simultaneously. Extensive experiments have been done on a real-world fake news dataset to compare FAKEDETECTOR with several state-of-the-art models, and the experimental results are provided in the full-version of this paper at [13].

We analyzed the temporal aspect of trends and trend-setters in Sina Weibo, contrasting it with earlier observations of Twitter. We found a vast difference in the content shared in China as compared with a global social network such as Twitter. In China, the trends are created almost entirely due to the retweets of media content such as jokes, images, and videos, unlike Twitter where trends have more to do with current global events and news stories. On closer inspection, we observed that most trends in Sina Weibo are due to the continuous retweets of a small percentage of fraudulent accounts, set up to artificially inflate certain posts. This reveals evidence of an “Internet Water Army,” a unique promotional method deployed by public relations companies in China to influence the popular dissemination of information in online social networks.

Over the years, online social networks (OSNs) have become popular form of networks for people to create and maintain networks of friends, to share knowledge/interests, and to publish content on a massive scale. The popularity of such OSNs has formed a virtual platform for viral marketing of contents, products, target advertising, and political campaigns. The amount of work dedicated to studying information diffusion in OSNs has increased in recent years. Past research has clearly shown that diffusion of information in social networks depends on both the nature of the information and the structure of the network. In this study, we focus on one of the structural properties, tie strength, in the flow of information through social networks. Several studies have shown that weak ties can act as bridges, linking disconnected groups in the network, which, in turn, allows information to diffuse between subgroups. However, not all weak ties are good weak ties in the network. In this study, we want to prove that a weak tie helps in the spread of information, when a good weak tie is selected. Specifically, we proposed a simple mechanism to select good weak ties in each step of the propagation process. We simulate our mechanism on data collected from two blog networks (wretch.cc and tribe.com) and a Facebook network, and found that an appropriate weak tie can improve the diffusion of information.

Online Social Networks (OSN) are getting popular day by day. Users share their information in OSN with others users. Access control is required to prevent unauthorized access to this information. Several studies have been conducted for access control in social networks. This chapter is a survey of available access control models/techniques based on social networks. Available access control models can be categorized as relationship-based, attributes-based, community structure-based and user activity centric model. A number of techniques have been proposed by several authors for access control in social networks. Most of the approaches use Social Network Analysis (SNA) techniques, others use user related information, for example, attributes or activities, the rest use a combination of approaches.

In recent years, due to the booming development of online social networks, fake news has been appearing in large numbers and widespread in the online world. With deceptive words, online social network users can get infected by these online fake news easily, which has brought about tremendous effects on the offline society already. An important goal in improving the trustworthiness of information in online social networks is to identify the fake news timely. However, fake news detection remains to be a challenge, primarily because the content is crafted to resemble the truth in order to deceive readers, and without fact-checking or additional information, it is often hard to determine veracity by text analysis alone. In this paper, we first proposed multi-level convolutional neural network (MCNN), which introduced the local convolutional features as well as the global semantics features, to effectively capture semantic information from article texts which can be used to classify the news as fake or not. We then employed a method of calculating the weight of sensitive words (TFW), which has shown their stronger importance with their fake or true labels. Finally, we develop MCNN-TFW, a multiple-level convolutional neural network-based fake news detection system, which is combined to perform fake news detection in that MCNN extracts article representation and WS calculates the weight of sensitive words for each news. Extensive experiments have been done on fake news detection in cultural communication to compare MCNN-TFW with several state-of-the-art models, and the experimental results have demonstrated the effectiveness of the proposed model.

Ultra-efficient information detection on large-scale online social networks

Consequences of Publishing Real Personal Information in Online Social Networks

In this work, we address the problem of distributed expert finding using chains of social referrals and profile matching with only local information in online social networks. By assuming that users are selfish, rational, and have privately known cost of participating in the referrals, we design a novel truthful efficient mechanism in which an expert-finding query will be relayed by intermediate users. When receiving a referral request, a participant will locally choose among her neighbors some user to relay the request. In our mechanism, several closely coupled methods are carefully designed to improve the performance of distributed search, including, profile matching, social acquaintance prediction, score function for locally choosing relay neighbors, and budget estimation. We conduct extensive experiments on several data sets of online social networks. The extensive study of our mechanism shows that the success rate of our mechanism is about 90 percent in finding closely matched experts using only local search and limited budget, which significantly improves the previously best rate 20 percent. The overall cost of finding an expert by our truthful mechanism is about 20 percent of the untruthful methods, e.g., the method that always selects high-degree neighbors. The median length of social referral chains is 6 using our localized search decision, which surprisingly matches the well-known small-world phenomenon of global social structures.

The outbreak of the COVID-19 led to a burst of information in major online social networks (OSNs). Facing this constantly changing situation, OSNs have become an essential platform for people expressing opinions and seeking up-to-the-minute information. Thus, discussions on OSNs may become a reflection of reality. This paper aims to figure out how Twitter users in the Greater Region (GR) and related countries react differently over time through conducting a data-driven exploratory study of COVID-19 information using machine learning and representation learning methods. We find that tweet volume and COVID-19 cases in GR and related countries are correlated, but this correlation only exists in a particular period of the pandemic. Moreover, we plot the changing of topics in each country and region from 22 January 2020 to 5 June 2020, figuring out the main differences between GR and related countries.

In the new economic context, the on-line social networks (OSN) are gathering among their users a whole array of persons, with a diversified background, culture, opinions and needs. Here is the meeting point for persons looking for information on different domains and areas of interest and also here is the exchange land for thoughts, experiences, news, etc. As the companies have sensed the global phenomenon of the OSN, they have paid more attention to the on-line social environment, investing more in the social media campaigns. But what about the companies in the healthcare system? Are their customers seeking for information in OSN? And if so, to what extent the information provided here is useful? Namely, is the OSN affecting their performance?

The credibility of information in social networks has attracted a lot of interest due to its important role in spreading information. We argue that the quality of information or objects created in social networks can be analyzed by using their provenance data. In this paper, we propose an algorithm that assesses the credibility of information on social networks to detect the propagation of fake or malicious information. To test the usability of the proposed algorithm, we introduce a prototype implementation and discuss it in detail. We test the prototype software on a large-scale synthetic social provenance dataset. The initial results are promising.

Based on the complex network theory and topological properties of scale-free network, a new information propagation model (Susceptible Exposed Inactive Infected Recovered, SEIIR) and dynamic evolution equations are proposed based on microblog social network in this paper. Firstly, we analyze the structure of microblog social network through simulating the real microblog social network environment, and the topological properties of the microblog network are researched. Secondly, microblog network structure and topological properties, traditional information propagation models (SIR, SIRS and SEIR) and evolution mechanism are also studied. Dynamic evolution equations of information propagation are constructed in microblog network, and nonlinear dynamic information propagation model is proposed. Effect factors of the information propagation process in microblog network are investigated. Finally, a series of simulation experiments are carried out. Simulation results show that the proposed new SEIIR model and information propagation dynamic evolution equations are reasonable and effective. It reveals the relationship between the state of microblog social network nodes and the evolution public opinion. It accurately depicts the information interaction mechanism and diffusion pattern in online social network. It provides a new scientific method and research approach for the study of social network public opinion evolution and information propagation.

A lot of malicious information such as rumours are hidden in the massive data flow in social online networks. Once this type of malicious information spreads, it could affect social stability in severe cases. This paper introduces the concept of trusted regulator to select key nodes, and we propose a method to hinder the rapid spread of malicious information by blocking accounts and publishing clarification, so that the external disturbances from the chosen nodes and the malicious information could fight against each other. Local control strategy is applied to the propagation of malicious information. Specifically, we first introduce the SIMRT model and an importance indicator based on edge weight, then we propose the reverse intervention algorithm based on the importance indicator. Experiment results on different data sets show that the proposed algorithm can effectively suppress the spread of malicious information.