Search

Communities in social networks are groups of individuals who are connected with specific goals. Discovering information on the structure, members and types of changes of communities have always been of great interest. Despite the extensive global researches conducted on these, discovery has not been confirmed yet and researchers try to find methods and improve estimated techniques by using Data Mining tools, Graph Mining tools and artificial intelligence techniques. This paper proposes a novel two-phase approach based on global and local information to detect communities in social network. It explores the global information in the first phase and then exploits the local information in the second phase to discover communities more accurately. It also proposes a novel algorithm which exploits the local information and mines deeply for the second phase. Experimental results show that the proposed method has better performance and achieves more accurate results compared with the previous ones. [ABSTRACT FROM AUTHOR]

With the rapid development of the Internet, the computational analysis of social networks has grown to be a salient issue. Various research analyses social network topics, and a considerable amount of attention has been devoted to the issue of link prediction. Link prediction aims to predict the interactions that might occur between two entities in the network. To this aim, this study proposed a novel path and node combined approach and constructed a methodology for measuring node similarities. The method was illustrated with five real datasets obtained from different types of social networks. An extensive comparison of the proposed method against existing link prediction algorithms was performed to demonstrate that the path and node combined approach achieved much higher mean average precision (MAP) and area under the curve (AUC) values than those that only consider common nodes (e.g. Common Neighbours and Adamic/Adar) or paths (e.g. Random Walk with Restart and FriendLink). The results imply that two nodes are more likely to establish a link if they have more common neighbours of lower degrees. The weight of the path connecting two nodes is inversely proportional to the product of degrees of nodes on the pathway. The combination of node and topological features can substantially improve the performance of similarity-based link prediction, compared with node-dependent and path-dependent approaches. The experiments also demonstrate that the path-dependent approaches outperform the node-dependent appraoches. This indicates that topological features of networks may contribute more to improving performance than node features. [ABSTRACT FROM AUTHOR]

Social recommender systems aim to support user preferences and help users make better decisions in social media. The social network and the social context are two vital elements in social recommender systems. In this contribution, we propose a new framework for a social recommender system based on both network structure analysis and social context mining. Exponential random graph models (ERGMs) are able to capture and simulate the complex structure of a micro-blog network. We derive the prediction formula from ERGMs for recommending micro-blog users. Then, a primary recommendation list is created by analysing the micro-blog network structure. In the next step, we calculate the sentiment similarities of micro-blog users based on a sentiment feature set which is extracted from users’ tweets. Sentiment similarities are used to filter the primary recommendation list and find users who have similar attitudes on the same topic. The goal of those two steps is to make the social recommender system much more precise and to satisfy users’ psychological preferences. At the end, we use this new framework deal with big real-world data. The recommendation results of diabetes accounts of Weibo show that our method outperforms other social recommender systems. [ABSTRACT FROM AUTHOR]

Among the applications of Web 2.0, social networking sites continue to proliferate and the volume of content keeps growing; as a result, information overload causes difficulty for users attempting to choose useful and relevant information. To resolve this problem, most researches only utilize users’ preferences, the content of items or social influence to make recommendations. However, people’s preferences for items may be affected by social friends, personal interest and item popularity. Moreover, each factor has a different impact on each user. In this work, we propose a novel recommendation method based on different types of influences: social, interest and popularity, using personal tendencies in regard to these factors to recommend photos in a photo-sharing website, Flickr. The personal tendencies related to these three influences are regarded as personalized weights to combine influence scores for predicting the scores of items. The experimental results show that our proposed methods can improve the quality of recommendations. [ABSTRACT FROM AUTHOR]

The increasing popularity of the social networking service, Twitter, has made it more involved in day-to-day communications, strengthening social relationships and information dissemination. Conversations on Twitter are now being explored as indicators within early warning systems to alert of imminent natural disasters such as earthquakes and aid prompt emergency responses to crime. Producers are privileged to have limitless access to market perception from consumer comments on social media and microblogs. Targeted advertising can be made more effective based on user profile information such as demography, interests and location. While these applications have proven beneficial, the ability to effectively infer the location of Twitter users has even more immense value. However, accurately identifying where a message originated from or an author’s location remains a challenge, thus essentially driving research in that regard. In this paper, we survey a range of techniques applied to infer the location of Twitter users from inception to state of the art. We find significant improvements over time in the granularity levels and better accuracy with results driven by refinements to algorithms and inclusion of more spatial features. [ABSTRACT FROM AUTHOR]

One of the fundamental issues in social networks is the influence maximization problem, where the goal is to identify a small subset of individuals such that they can trigger the largest number of members in the network. In real-world social networks, the propagation of information from a node to another may incur a certain amount of time delay; moreover, the value of information may decrease over time. So not only the coverage size, but also the propagation speed matters. In this paper, we propose the Time-Sensitive Influence Maximization (TSIM) problem, which takes into account the time dependence of the information value. Considering the time delay aspect, we develop two diffusion models, namely the Delayed Independent Cascade model and the Delayed Linear Threshold model. We show that the TSIM problem is NP-hard under these models but the spread function is monotone and submodular. Thus, a greedy approximation algorithm can achieve a 1 − 1/e approximation ratio. Moreover, we propose two time-sensitive centrality measures and compare their performance with the greedy algorithm. We evaluate our methods on four real-world datasets. Experimental results show that the proposed algorithms outperform existing methods, which ignore the decay of information value over time. [ABSTRACT FROM AUTHOR]

Studies on friendships in online social networks involving geographic distance have so far relied on the city location provided in users’ profiles. Consequently, most of the research on friendships has provided accuracy at the city level, at best, to designate a user’s location. This study analyses a Twitter dataset because it provides the exact geographic distance between corresponding users. We start by introducing a strong definition of ‘friend’ on Twitter (i.e. a definition of bidirectional friendship), requiring bidirectional communication. Next, we utilize geo-tagged mentions delivered by users to determine their locations, where ‘@username’ is contained anywhere in the body of tweets. To provide analysis results, we first introduce a friend-counting algorithm. From the fact that Twitter users are likely to post consecutive tweets in the static mode, we also introduce a two-stage distance-estimation algorithm. As the first of our main contributions, we verify that the number of friends of a particular Twitter user follows a well-known power-law distribution (i.e. a Zipf’s distribution or a Pareto distribution). Our study also provides the following newly discovered friendship degree related to the issue of space: the number of friends according to distance follows a double power-law (i.e. a double Pareto law) distribution, indicating that the probability of befriending a particular Twitter user is significantly reduced beyond a certain geographic distance between users, termed the separation point. Our analysis provides concrete evidence that Twitter can be a useful platform for assigning a more accurate scalar value to the degree of friendship between two users. [ABSTRACT FROM AUTHOR]

This paper presents a study on factors that may increase the risks of personal information leakage, owing to the possibility of connecting user profiles that are not explicitly linked together. First, we introduce a technique for user identification based on cross-site checking and linking of user attributes. Then, we describe the experimental evaluation of the identification technique both in a real setting and on an online sample, showing its accuracy to discover unknown personal data. Finally, we combine the results on the accuracy of identification with the results of a questionnaire completed by the same subjects who performed the test in the real setting. The aim of the study was to discover possible factors that make users vulnerable to this kind of technique. We found that the number of social networks used, their features and especially the amount of profiles abandoned and forgotten by the user are factors that increase the likelihood of identification and the privacy risks. [ABSTRACT FROM PUBLISHER]

Social network analysis has been used to study complex networks by analysing their static structure and the dynamic changes. Although one of the newer forms of social media, micro-blogs have quickly become one of the most popular communication platforms. This popularity accounts for, in part, an increase in the scientific interest in micro-blogs and their users. In this paper, we chose as our test bed diabetes-related posts from the Chinese micro-blog Sina Weibo. We calculated the degree, average shortest path, betweenness and clustering coefficient of the Sian Weibo network to analyse its static structure. We demonstrate the characteristic results of average degree, diameter and clustering coefficient of diabetes micro-blog static structure. More importantly, we introduce a general model for micro-blog with directed network data, Exponential-family Random Graph Models (ERGMs). Meanwhile, we illustrate the utility for estimating, analysing and simulating micro-blog network. We also provide a goodness-of-fit approach to capture and reproduce the structure of the fitted micro-blog network. Parameter estimation of the model, similarity results of simulated networks and observed networks, and goodness of fit analysis for the micro-blog network all illustrate that ERGMs are excellent methods for deeply capturing complex network structures. [ABSTRACT FROM PUBLISHER]