جستجوی مقالات مرتبط با کلیدواژه « Social networks » در نشریات گروه « برق »

Nowadays, social networks are recognized as significant sources of information exchange. Consequently, many organizations have chosen social networks as essential tools for marketing and brand management. Communities are essential structures that can enhance the performance of social networks by grouping nodes and analyzing the information derived from them. This subject becomes more important with the increase in information volume and the complexity of relationships in networks. The goal of community identification is to find subgraphs that are densely connected internally but loosely connected externally. While community detection has mostly been studied in static networks in the past, this paper focuses on dynamic networks and the influence of central nodes in forming communities. In the proposed algorithm, the network is captured through multiple snapshots. The initial snapshot calculates the influence of each node. Then, by selecting k nodes with higher influence, network communities are formed, and other nodes belong to the community with the most common edges. In the second step, after receiving the next snapshot, communities are updated. Then, k nodes with higher influence are selected, and their associated community is created if needed. If the previous community centers are not among the newly selected k nodes, the community is dissolved, and the nodes within it belong to other communities. Based on the results obtained, the proposed algorithm has managed to achieve better results in most cases compared to the compared algorithms, especially in terms of modularity metrics. The reason behind this success could be attributed to the utilization of influential nodes in community formation. Drawing from the outcomes attained, the suggested algorithm has effectively outperformed the contrasted algorithms in a majority of instances, particularly concerning metrics related to modularity. This accomplishment can potentially be ascribed to the incorporation of influential nodes during the process of community formation.

Analyzing the influence of people and nodes in social networks has attracted a lot of attention. Social networks gain meaning, despite the groups, associations, and people interested in a specific issue or topic, and people demonstrate their theoretical and practical tendencies in such places. Influential nodes are often identified based on the information related to the social network structure and less attention is paid to the information spread by the social network user. The present study aims to assess the structural information in the network to identify influential users in addition to using their information in the social network. To this aim, the user’s feelings were extracted. Then, an emotional or affective score was assigned to each user based on an emotional dictionary and his/her weight in the network was determined utilizing centrality criteria. Here, the Twitter network was applied. Thus, the structure of the social network was defined and its graph was drawn after collecting and processing the data. Then, the analysis capability of the network and existing data was extracted and identified based on the algorithm proposed by users and influential nodes. Based on the results, the nodes identified by the proposed algorithm are considered high-quality and the speed of information simulated is higher than other existing algorithms.

Link prediction (LP) has become a hot topic in the data mining, machine learning, and deep learning community. This study aims to implement bibliometric analysis to find the current status of the LP studies and investigate it from different perspectives. The present study provides a Scopus-based bibliometric overview of the LP studies landscape since 1987 when LP studies were published for the first time. Various kinds of analysis, including document, subject, and country distribution are applied. Moreover, author productivity, citation analysis, and keyword analysis is used, and Bradford’s law is applied to discover the main journals in this field. Most documents were published by conferences in the field. The majority of LP documents have been published in the computer science and mathematics fields. So far, China has been at the forefront of publishing countries. In addition, the most active sources of LP publications are lecture notes in Computer Science, including subseries lecture notes in Artificial Intelligence (AI) and lecture notes in Bioinformatics, and IEEE Access. The keyword analysis demonstrates that while social networks had attracted attention in the early period, knowledge graphs have attracted more attention, recently. Since the LP problem has been approached recently using machine learning (ML), the current study may inform researchers to concentrate on ML techniques. This is the first bibliometric study of “link prediction” literature and provides a broad landscape of the field.

Nowadays, Social media is heading toward personalization more and more. People express themselves and reveal their beliefs, interests, habits, and activities, simply giving a glimpse of their personality traits. The thing that pushed us toward further investigating the mutual relation between personality and social media, taking into consideration the shortage in covering such important topic, especially in rich morphological languages. In this paper, we work on the connection between usage of Arabic language on social outlets (mainly Facebook and Twitter) and personality traits. We indicate the personality traits of users based on the information extracted from their activities and the content of their posts/tweets in Social Networks. We use linguistic features, beside some other features like emoticons. We gathered personality data using Arabic personality test based on Myers-Briggs Type Indicator (MBTI), which contains Thinking, Feeling, Intuition, Introversion, Sensation, Extroversion, Perceiving and Judgement traits. We collected our dataset from 522 volunteers, who permitted us to crawl their tweets and posts in Twitter and Facebook. Analysis of this dataset proved that some linguistic features could be used to differentiate between different personality traits. We used and implemented Deep Learning, and BERT to reveal personality and create a model for this purpose. Up to our knowledge, this is the first work on detection of personality traits from social network’s data in Arabic language.

The spread of internet and smartphones in recent years has led to the popularity and easy accessibility of social networks among users. Despite the benefits of these networks, such as ease of interpersonal communication and providing a space for free expression of opinions, they also provide the opportunity for destructive activities such as spreading false information or using fake accounts for fraud intentions. Fake accounts are mainly managed by bots. So, identifying bots and suspending them could very much help to increase the popularity and favorability of social networks. In this paper, we try to identify Persian bots on Twitter. This seems to be a challenging task in view of the problems pertinent to processing colloquial Persian. To this end, a set of features based on user account information and activity of users added to content features of tweets to classify users by several machine learning algorithms like Random Forest, Logistic Regression and SVM. The results of experiments on a dataset of Persian-language users show the proper performance of the proposed methods. It turns out that, achieving a balanced-accuracy of 93.86%, Random Forest is the most accurate classifier among those mentioned above.

One of the most important technologies that has affected our lives today is cyberspace. On the other hand, one of the most important problems of social networks is the disclosure of users' information, i.e. the violation of their privacy. Therefore, protecting the privacy of users is very important, so the use of encryption methods is an important tool in ensuring the privacy and security of shared data users. The proposed framework of this paper is based on AES and RSA algorithms. This framework is designed to be decentralized and takes advantage of the AES and RSA algorithms to provide a framework that prevents unauthorized entities from accessing users' data and messages. Any safe method must be designed in such a way that there is no escape route for attackers and unauthorized entities. Therefore, our focus is on two important parts of secure methods, namely key management and privacy, which the results of this article show, the security assessment proved that our proposed framework is designed to be completely safe and correct, and increased security and efficiency.

This paper presents a novel approach for the statistical monitoring of online social networks where the edges represent the count of communications between ties at each time stamp. Since the available methods in the literature are limited to the assumption that the set of all interacting individuals is fixed during the monitoring horizon and their corresponding attributes do not change over time, the proposed method tackles these limitations due to the properties of the random effects concepts. Applying appropriate parameters estimation technique involved in a likelihood ratio testing (LRT) approach considering two different statistics, the longitudinal network data are monitored. The performance of the proposed method is verified using numerical examples including simulation studies as well as an illustrative example.

Telegram is a cloud-based instant messenger with more than 500 million monthly active users. This messenger is very popular among Iranians, as more than 50 million Telegram users are Iranians. Telegram is used as a social network in Iran because it offers features beyond a simple messenger, but does not offer all the features of social networks, including user recommendation. In this paper, investigating a real dataset crawled from Telegram, we have provided a hybrid method using the user membership graph and group characteristics to recommend the user in Telegram. The membership graph connects users based on membership in the same groups. Also, the characteristics for each group are indicated by the name and description of that group in Telegram. We created a bag of words for each group using natural language processing methods, then combined the bag of words for each group with the results of the membership graph processing. Finally, users are recommended based on the list of groups obtained by the combination. The data used in this paper include more than 900,000 groups and 120 million users. Evaluation of the proposed method separately on two categories of Telegram specialized groups shows the model integration and error reduction for the first category to 0.009 and the second category to 0.016 in RMSE.

Recommender systems has an important role in social networks. With the growth and development ofsocial networks, this issue is becoming more and more important. Recommending systems try to predict the user's interests and then suggest the closest items to the user's tastes. Recommender systems analyze the user’s behavior and suggest the most appropriate items. By collecting user information, the system categorizes and summarizes them, allowing users to access more relevant information in less time. Recommender system is an intelligent system that creates appropriate suggestions for each person by discovering and analyzing user information.In this paper, we will investigate recommending systems in three sections: types of recommendingsystems, information confidentiality and trust in recommender systems. We will refer to the relatedworks in each section, review the challenges of them, and present our results and evaluation on thesemethods