Context Aware Sentiment Link Prediction in Heterogeneous Social Network

Currently, online social networks and social media have become increasingly popular showing an exponential growth. This fact have attracted increasing research interest and, in turn, facilitating the emergence of new interdisciplinary research directions, such as social network analysis. In this scenario, link prediction is one of the most important tasks since it deals with the problem of the existence of a future relation among members in a social network. Previous techniques for link prediction were based on structural (or topological) information. Nevertheless, structural information is not enough to achieve a good performance in the link prediction task on large-scale social networks. Thus, the use of additional information, such as interests or behaviors that nodes have into their communities, may improve the link prediction performance. In this paper, we analyze the viability of using a set of simple and non-expensive techniques that combine structural with community information for predicting the existence of future links in a large-scale online social network, such as Twitter. Twitter, a microblogging service, has emerged as a useful source of informative data shared by millions of users whose relationships require no reciprocation. Twitter network was chosen because it is not well understood, mainly due to the occurrence of directed and asymmetric links yet. Experiments show that our proposals can be used efficiently to improve unsupervised and supervised link prediction task in a directed and asymmetric large-scale network.

Heterogeneous social networks, which are characterized by diverse interaction types, have resulted in new challenges for missing link prediction. Most deep learning models tend to capture type-specific features to maximize the prediction performances on specific link types. However, the types of missing links are uncertain in heterogeneous social networks; this restricts the prediction performances of existing deep learning models. To address this issue, we propose a multi-type transferable method ( <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">MTTM</i> ) for missing link prediction in heterogeneous social networks, which exploits adversarial neural networks to remain robust against type differences. It comprises a generative predictor and a discriminative classifier. The generative predictor can extract link representations and predict whether the unobserved link is a missing link. To generalize well for different link types to improve the prediction performance, it attempts to deceive the discriminative classifier by learning transferable feature representations among link types. In order not to be deceived, the discriminative classifier attempts to accurately distinguish link types, which indirectly helps the generative predictor judge whether the learned feature representations are transferable among link types. Finally, the integrated <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">MTTM</i> is constructed on this minimax two-player game between the generative predictor and discriminative classifier to predict missing links based on transferable feature representations among link types. Extensive experiments show that the proposed <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">MTTM</i> can outperform state-of-the-art baselines for missing link prediction in heterogeneous social networks.

The Hypertext 2015 Doctorial Consortium session is held the first day of the 26th ACM Conference on Hypertext and Social Media. It offers Ph.D. students an opportunity to present their ongoing research towards obtaining a Ph.D. degree in the disciplines related to the conference, mostly in Computer and Information Sciences but not limited to them. The themes of the submissions are strongly connected to the research tracks of this year's conference: Digital Connectivity, Data Connectivity and Digital Humanities. The Digital Connectivity track targets developing insights into the mechanisms of information generation and dissemination, characterization of evolutionary processes on online social networks, and studies of models and systems that support these processes. The second track, Data Connectivity, deals with the methods, techniques and technologies that can be used to make data available on the Web, with a special focus on how heterogeneous data sources can be connected to each other. Finally, the track of Digital Humanities seeks to attract work from an interdisciplinary perspective, on the intersection between computer science on one hand, and the humanities and social sciences on the other. During the DC session, students receive constructive feedback from their peers and from a panel of mentors to support them in envisioning added-value contributions to the state-of-the-art research in Hypertext and Social Media. The consortium session is open to all doctorial students by application. Each submission was reviewed by three senior researchers in the topics the students made their submissions. The DC session is aimed in particular at students who have defined a dissertation topic but are still more than one year from graduating at the time of application in order to obtain benefits from feedback. This year, the committee has accepted three contributions to be presented during the Doctorial Consortium session: Automated Methods for Identity Resolution in Heterogeneous Social Platforms by Paridhi Jahin. In this work, connected to the digital and data connectivity tracks of the conference, the author proposes novel methods to search and link user identities scattered across heterogeneous social networks. The methods consider carefully users' privacy, so they are designed to access only public and historic data. The evaluation is proposed on large datasets over multiple platforms to prove their significance in identity resolution of an online user. Language Innovation and Change in On-line Social Networks by Daniel Kershaw. As a fundamental aspect for human communication, this research focuses on forecasting online language change through the use of predictive and descriptive methodologies. This work is framed within structuration theory which helps the researcher in structuring the analysis of the dynamics of language (re)production - i.e. by the agent (user), the social structure and their interplay. A Framework to Provide Customized Reuse of Open Corpus Content for Adaptive Systems by Mostafa Bayomi. This work deals with issues of reusability of contents on adaptive systems. Adaptive systems tailor content specific to user's needs, but they face two big problems: (a) they use a closed corpus content that has been prepared for them a priori, and (b) the content is tightly coupled with other parts of the system, which hinders its reusability. This work presents a proposal that leverages the semantic web by extending an existing content provision system, Slice-pedia.

Using a cross-sectional survey of two sampled counties in Kenya, this article analyses whether social networking sites reflect social network heterogeneity. It then examines how social network heterogeneity influences polarisation in Kenya. Three types of polarisation are examined: party, ethnic and ideological (around county resources). The study focuses specifically on the public WhatsApp platform (the most popular SNS in Kenya). To assess this empirical data, theoretical perspectives are drawn from the literatures on incidental and selective exposure and their impact on political polarisation. The findings indicate that the randomised composition of a WhatsApp group through public links indeed reflects social network heterogeneity. The findings further show that posting political news, obtaining political news and commenting on political news influence social network heterogeneity to some degree. This social network heterogeneity was also found to influence all three (party, ideological and ethnic) types of polarisation in varying but significant degrees.

Harnessing heterogeneous social networks for better recommendations: A grey relational analysis approach

The social network is a powerful data structure allowing the study of relationship information between entities. The existing methods only rely on analyzing homogeneous social network assuming only a single type of node and relation. Though, real world complex networks are not so. Usually it is a heterogeneous social network which assumes a network with different types of nodes and relation. A Multi Relational Network (MRN) is used to describe the nodes and links in the form of a directional semantic graph where each node is related with more than one relationship with others. The profile for each node can be generated based on the relation sequence of each node. To analyze the relation of node in the heterogeneous social network, role analysis is done in the profile creation. The evaluations are conducted on a real-world movie dataset with promising results.

User identity linkage has important implications in many cross-network applications, such as user profile modeling, recommendation and link prediction across social networks. To discover accurate cross-network user correspondences, it is a critical prerequisite to find effective user representations. While structural and content information describe users from different perspectives, there is a correlation between the two aspects of information. For example, a user who follows a celebrity tends to post content about the celebrity as well. Therefore, the projections of structural and content information of a user should be as close to each other as possible, which inspires us to fuse the two aspects of information in a unified space. However, owing to the information heterogeneity, most existing methods extract features from content and structural information respectively, instead of describing them in a unified way. In this paper, we propose a Linked Heterogeneous Network Embedding model (LHNE) to learn the comprehensive representations of users by collectively leveraging structural and content information in a unified framework. We first model the topics of user interests from content information to filter out noise. Next, cross-network structural and content information are embedded into a unified space by jointly capturing the friend-based and interest-based user co-occurrence in intra-network and inter-network, respectively. Meanwhile, LHNE learns user transfer and topic transfer for enhancing information exchange across networks. Empirical results show LHNE outperforms the state-of-the-art methods on both real social network and synthetic datasets and can work well even with little or no structural information.

3D graph neural network with few-shot learning for predicting drug–drug interactions in scaffold-based cold start scenario

This study provides a conceptual framework for understanding how the graduate acquire employability through the social network in the Chinese context, using insights from the social network theory. This paper builds a conceptual model of the relationship among social network, social network learning and the graduate employability, and uses structural equation analysis method to conduct an empirical test on the theoretical hypothesis, based on a sample of 1468 fresh graduates of business discipline from the local university in Zhejiang province of China. The findings suggested that social network is one of the important platforms for graduate to acquire employability in China, the scale of social network, social network heterogeneity and the strength of the relationship have positive effects on the formation of graduate employability. The acquisition mode of employability based on the social network can be divided into imitation learning, communication learning, accepting guidance, these three kinds of learning mode have positive effects on the formation of graduate employability, and play a mediating role in the relationship between social networks and graduate employability. University graduate should pay attention to the shaping of learning behavior based on social network to improve their employability in China.

The online social network alignment problem aims at inferring the anchor links connecting the shared users across social networks, which are usually subject to the one-to-one cardinality constraint. Several existing social network alignment models have been proposed, many of which are based on the supervised learning setting. Given a set of labeled anchor links, a group of features can be extracted manually for the anchor links to build these models. Meanwhile, such methods may encounter great challenges in the application on real-world social network datasets, since manual feature extraction can be extremely expensive and tedious for the social networks involving heterogeneous information. In this paper, we propose to address the heterogeneous social network alignment problem with a deep learning model, namely DETA (Deep nETwork Alignment). Besides a small number of explicit features, DETA can automatically learn a set of latent features from the heterogeneous information. DETA models the anchor link one-to-one cardinality constraint as a mathematical constraint on the node degrees. Extensive experiments have been done on real-world aligned heterogeneous social network datasets, and the experimental results have demonstrated the effectiveness of the proposed model compared against the existing state-of-the-art baseline methods.

Accurate user representation learning has been proven fundamental for many social media applications, including community detection, recommendation, etc. A major challenge lies in that, the available data in a single social network are usually very limited and sparse. In real life, many people are members of several social networks in the same time. Constrained by the features and design of each, any single social platform offers only a partial view of a user from a particular perspective. In this paper, we propose MV-URL, a multi-view user representation learning model to enhance user modeling by integrating the knowledge from various networks. Different from the traditional network embedding frameworks where either the whole framework is single-network based or each network involved is a homogeneous network, we focus on multiple social networks and each network in our task is a heterogeneous network. It's very challenging to effectively fuse knowledge in this setting as the fusion depends upon not only the varying relatedness of information sources, but also the target application tasks. MV-URL focuses on two tasks: user account linkage (i.e., to predict the missing true user account linkage across social media) and user attribute prediction. Extensive evaluations have been conducted on two real-world collections of linked social networks, and the experimental results show the superiority of MV-URL compared with existing state-of-art embedding methods. It can be learned online, and is trivially parallelizable. These qualities make it suitable for real world applications.

We study the dynamics of social networks in terms of population growth and control of user behavior. Most of the current research in social networks focus on static analysis through graph theoretic models to represent the networks or focus on modeling the traffic. Here, we study the cost of collaborative vs individualistic behavior of users in order to grow their network size in a social network. Each user incurs a cost (monetary or emotional) for collaboration. We formulate the behavior of the users as a non-linear optimization problem with a cost. The objective function of the optimization problem is obtained using a stochastic analysis of population growth in social networks, based on the first-passage time of a birth-death process. The stochastic model is validated by comparison with real data obtained from Twitter Results indicate that a homogeneous social network (in which users have similar characteristics) will be individualistic. However, heterogeneous social networks (users with different characteristics) exhibit a threshold effect, i.e., there is a minimum cost, below which the network is as collaborative as desired and a maximum cost above which the network is individualistic as required. To the best of our knowledge, this is one of the first analysis of dynamics of user behavior and temporal population growth in social networks.

The problem of privacy-preserving data mining has attracted considerable attention in recent years because of increasing concerns about the privacy of the underlying data. In recent years, an important data domain which has emerged is that of graphs and structured data. Many data sets such as XML data, transportation networks, traffic in IP networks, social networks and hierarchically structured data are naturally represented as graphs. Existing work on graph privacy has focussed on the problem of anonymizing nodes or edges of a single graph, in which the identity is assumed to be associated with individual nodes. In this paper, we examine the more complex case, where we have a collection of graphs, and the identity is associated with individual graphs rather than nodes or edges. In such cases, the problem of identity anonymization is extremely difficult, since we need to not only anonymize the labels on the nodes, but also the underlying global structural information. In such cases, both the global and local structural information can be a challenge to the anonymization process, since any combination of such information can be used in order to de-identify the underlying graphs. In order to achieve this goal, we will create synthesized representations of the underlying graphs based on aggregate structural analytics of the collection of graphs. The synthesized graphs retain the properties of the original data while satisfying the k-anonymity requirement. Our experimental results show that the synthesized graphs maintain a high level of structural information and compatible classification accuracies with the original data.

Many famous online social networks, e.g., Facebook and Twitter, have achieved great success in the last several years. Users in these online social networks can establish various connections via both social links and shared attribute information. Discovering groups of users who are strongly connected internally is defined as the community detection problem. Community detection problem is very important for online social networks and has extensive applications in various social services. Meanwhile, besides these popular social networks, a large number of new social networks offering specific services also spring up in recent years. Community detection can be even more important for new networks as high quality community detection results enable new networks to provide better services, which can help attract more users effectively. In this paper, we will study the community detection problem for new networks, which is formally defined as the “New Network Community Detection” problem. New network community detection problem is very challenging to solve for the reason that information in new networks can be too sparse to calculate effective similarity scores among users, which is crucial in community detection. However, we notice that, nowadays, users usually join multiple social networks simultaneously and those who are involved in a new network may have been using other well-developed social networks for a long time. With full considerations of network difference issues, we propose to propagate useful information from other well-established networks to the new network with efficient information propagation models to overcome the shortage of information problem. An effective and efficient method, Cat (Cold stArT community detector), is proposed in this paper to detect communities for new networks using information from multiple heterogeneous social networks simultaneously. Extensive experiments conducted on real-world heterogeneous online social networks demonstrate that Cat can address the new network community detection problem effectively.

Automated online profiling consists of the accurate identification and linking of multiple online identities across heterogeneous online social networks that correspond to the same entity in the physical world. The paper proposes a hybrid profile correlation model which relies on a diversity of techniques from different application domains, such as record linkage and data integration, image and text similarity, and machine learning. It involves distance-based comparison methods and the exploitation of information produced by a social network identification process for use as external knowledge towards searches on other social networks; thus, the remaining identification tasks for the same individual are optimized. The experimental study shows that, even with limited resources, the proposed method collects and combines accurate information effectively from different online sources in a fully-automated way. The mined knowledge then becomes a powerful toolkit to carry out social engineering and other attacks, or for profit and decision-making data mining purposes.