scholarly journals Social behavior prediction with graph U-Net+

2021 ◽  
Vol 1 (1) ◽  
Author(s):  
Zhiyue Yan ◽  
Wenming Cao ◽  
Jianhua Ji
Keyword(s):  
Social Networks ◽  
Social Media ◽  
Feature Extraction ◽  
Binary Classification ◽  
Representation Learning ◽  
Graph Representation ◽  
Behavior Prediction ◽  
Graph Node ◽  
Future Behavior ◽  
Decoder Architecture

AbstractWe focus on the problem of predicting social media user’s future behavior and consider it as a graph node binary classification task. Existing works use graph representation learning methods to give each node an embedding vector, then update the node representations by designing different information passing and aggregation mechanisms, like GCN or GAT methods. In this paper, we follow the fact that social media users have influence on their neighbor area, and extract subgraph structures from real-world social networks. We propose an encoder–decoder architecture based on graph U-Net, known as the graph U-Net+. In order to improve the feature extraction capability in convolutional process and eliminate the effect of over-smoothing problem, we introduce the bilinear information aggregator and NodeNorm normalization approaches into both encoding and decoding blocks. We reuse four datasets from DeepInf and extensive experimental results demonstrate that our methods achieve better performance than previous models.

scholarly journals Pairwise Half-graph Discrimination: A Simple Graph-level Self-supervised Strategy for Pre-training Graph Neural Networks

2021 ◽  
Author(s):  
Pengyong Li ◽  
Jun Wang ◽  
Ziliang Li ◽  
Yixuan Qiao ◽  
Xianggen Liu ◽  
...  
Keyword(s):  
Neural Networks ◽  
Supervised Learning ◽  
Learning Strategy ◽  
Binary Classification ◽  
Representation Learning ◽  
Graph Representation ◽  
Superior Performance ◽  
Graph Classification ◽  
Training Strategy ◽  
Graph Neural Networks

Self-supervised learning has gradually emerged as a powerful technique for graph representation learning. However, transferable, generalizable, and robust representation learning on graph data still remains a challenge for pre-training graph neural networks. In this paper, we propose a simple and effective self-supervised pre-training strategy, named Pairwise Half-graph Discrimination (PHD), that explicitly pre-trains a graph neural network at graph-level. PHD is designed as a simple binary classification task to discriminate whether two half-graphs come from the same source. Experiments demonstrate that the PHD is an effective pre-training strategy that offers comparable or superior performance on 13 graph classification tasks compared with state-of-the-art strategies, and achieves notable improvements when combined with node-level strategies. Moreover, the visualization of learned representation revealed that PHD strategy indeed empowers the model to learn graph-level knowledge like the molecular scaffold. These results have established PHD as a powerful and effective self-supervised learning strategy in graph-level representation learning.

scholarly journals Multi-Scale Graph Representation Learning for Autism Identification With Functional MRI

2022 ◽  
Vol 15 ◽  
Author(s):  
Ying Chu ◽  
Guangyu Wang ◽  
Liang Cao ◽  
Lishan Qiao ◽  
Mingxia Liu
Keyword(s):  
Feature Extraction ◽  
Functional Mri ◽  
Expert Knowledge ◽  
Spatial Scales ◽  
Representation Learning ◽  
Autism Spectrum ◽  
Clustering Coefficient ◽  
Graph Representation ◽  
Node Degree ◽  
Multi Scale

Resting-state functional MRI (rs-fMRI) has been widely used for the early diagnosis of autism spectrum disorder (ASD). With rs-fMRI, the functional connectivity networks (FCNs) are usually constructed for representing each subject, with each element representing the pairwise relationship between brain region-of-interests (ROIs). Previous studies often first extract handcrafted network features (such as node degree and clustering coefficient) from FCNs and then construct a prediction model for ASD diagnosis, which largely requires expert knowledge. Graph convolutional networks (GCNs) have recently been employed to jointly perform FCNs feature extraction and ASD identification in a data-driven manner. However, existing studies tend to focus on the single-scale topology of FCNs by using one single atlas for ROI partition, thus ignoring potential complementary topology information of FCNs at different spatial scales. In this paper, we develop a multi-scale graph representation learning (MGRL) framework for rs-fMRI based ASD diagnosis. The MGRL consists of three major components: (1) multi-scale FCNs construction using multiple brain atlases for ROI partition, (2) FCNs representation learning via multi-scale GCNs, and (3) multi-scale feature fusion and classification for ASD diagnosis. The proposed MGRL is evaluated on 184 subjects from the public Autism Brain Imaging Data Exchange (ABIDE) database with rs-fMRI scans. Experimental results suggest the efficacy of our MGRL in FCN feature extraction and ASD identification, compared with several state-of-the-art methods.

scholarly journals UserRBPM: User Retweet Behavior Prediction with Graph Representation Learning

2021 ◽  
Vol 2021 ◽  
pp. 1-17
Author(s):  
Huihui Guo ◽  
Li Yang ◽  
Zeyu Liu
Keyword(s):  
Social Influence ◽  
Information Dissemination ◽  
Representation Learning ◽  
Social Representation ◽  
Graph Representation ◽  
Behavior Prediction ◽  
Domain Experts ◽  
The Public ◽  
Convolutional Networks ◽  
Better Than

Social and information networks such as Facebook, Twitter, and Weibo have become the main social platforms for the public to share and exchange information, where we can easily access friends’ activities and in turn be influenced by them. Consequently, the analysis and modeling of user retweet behavior prediction have an important application value, such as information dissemination, public opinion monitoring, and product recommendation. Most of the existing solutions for user retweeting behavior prediction are usually based on network topology maps of information dissemination or designing various handcrafted rules to extract user-specific and network-specific features. However, these methods are very complex or heavily dependent on the knowledge of domain experts. Inspired by the successful use of neural networks in representation learning, we design a framework, UserRBPM, to explore potential driving factors and predictable signals in user retweet behavior. We use the graph embedding technology to extract the structural attributes of the ego network, consider the drivers of social influence from the spatial and temporal levels, and use graph convolutional networks and the graph attention mechanism to learn its potential social representation and predictive signals. Experimental results show that our proposed UserRBPM framework can significantly improve prediction performance and express social influence better than traditional feature engineering-based approaches.

Deep Attentive Multimodal Network Representation Learning for Social Media Images

2021 ◽  
Vol 21 (3) ◽  
pp. 1-17
Author(s):  
Feiran Huang ◽  
Chaozhuo Li ◽  
Boyu Gao ◽  
Yun Liu ◽  
Sattam Alotaibi ◽  
...  
Keyword(s):  
Social Networks ◽  
Social Media ◽  
Large Scale ◽  
Smart Cities ◽  
Representation Learning ◽  
Media Images ◽  
Social Image ◽  
Comprehensive Information ◽  
Intelligent Information ◽  
Low Dimensional

The analysis for social networks, such as the socially connected Internet of Things, has shown a deep influence of intelligent information processing technology on industrial systems for Smart Cities. The goal of social media representation learning is to learn dense, low-dimensional, and continuous representations for multimodal data within social networks, facilitating many real-world applications. Since social media images are usually accompanied by rich metadata (e.g., textual descriptions, tags, groups, and submitted users), simply modeling the image is not effective to learn the comprehensive information from social media images. In this work, we treat the image and its textual description as multimodal content, and transform other metainformation into the links between contents (such as two images marked by the same tag or submitted by the same user). Based on the multimodal content and social links, we propose a Deep Attentive Multimodal Graph Embedding model named DAMGE for more effective social image representation learning. We introduce both small- and large-scale datasets to conduct extensive experiments, of which the results confirm the superiority of the proposal on the tasks of social image classification and link prediction.

A managerial perspective on omnichannel e-customer

2020 ◽  
pp. 5-17
Author(s):  
Maria Teresa Cuomo ◽  
Francesca Ceruti ◽  
Alice Mazzucchelli ◽  
Alex Giordano ◽  
Debora Tortora
Keyword(s):  
Social Networks ◽  
Social Media ◽  
Empirical Analysis ◽  
Customer Experience ◽  
Tourism Industry ◽  
Point Of View ◽  
Social Commerce ◽  
Social Dimensions ◽  
Offline Channels ◽  
Managerial Perspective

The actual omnichannel customer uses indifferently both online and offline channels to express himself through consumption, which increasingly blends personal, cultural and social dimensions. In this perspective social media and social networks are able to assist e-retailers in their effort of creating a total e-customer experience, especially in the tourism industry, trying to satisfy their clients from the relational and commercial point of view. By means of an empirical analysis where managers were interviewed on the topic and its degree of application in the firms, the paper underlines how from the managerial point of view, that represents a new prospect on the topic, the expected shift from e-commerce to social commerce paradigm, facilitating the selling and buying of products and services by using various internet features, is nowadays not completely understood and realized.

Emotive Trending And Tracking of Tweets

2017 ◽  
Vol 7 (11) ◽  
pp. 25
Author(s):  
Sanjay Chhataru Gupta
Keyword(s):  
Social Networks ◽  
Social Media ◽  
Social Network ◽  
The Social ◽  
The World ◽  
Complex Events

Popularity of the social media and the amount of importance given by an individual to social media has significantly increased in last few years. As more and more people become part of the social networks like Twitter, Facebook, information which flows through the social network, can potentially give us good understanding about what is happening around in our locality, state, nation or even in the world. The conceptual motive behind the project is to develop a system which analyses about a topic searched on Twitter. It is designed to assist Information Analysts in understanding and exploring complex events as they unfold in the world. The system tracks changes in emotions over events, signalling possible flashpoints or abatement. For each trending topic, the system also shows a sentiment graph showing how positive and negative sentiments are trending as the topic is getting trended.

Influence of social networks on business processes’ development

2020 ◽  
Vol 19 (12) ◽  
pp. 2225-2252
Author(s):  
E.V. Popov ◽  
V.L. Simonova ◽  
O.V. Komarova ◽  
S.S. Kaigorodova
Keyword(s):  
Social Networks ◽  
Social Media ◽  
Business Models ◽  
Business Processes ◽  
Digital Economy ◽  
Theoretical Understanding ◽  
Sales Channels ◽  
A Value ◽  
The Impact

Subject. The emergence of new ways of interaction between sellers and buyers, the formation of new sales channels and product promotion based on the use of digital economy tools is at the heart of improving the business processes. Social networks became a tool for development; their rapid growth necessitates theoretical understanding and identification of potential application in enterprise's business process digitalization. Objectives. We explore the role of social media in the digitalization of business processes, systematize the impact of social networks on business processes of enterprises in the digital economy. Methods. The theoretical and methodological analysis of social networks as a tool for digitalization of company's business processes rests on the content analysis of domestic and foreign scientific studies, comparison, generalization and systematization. Results. We highlight the key effects of the impact of social networks on the business processes of the company; show that the digitalization of business processes should be considered in the context of a value-based approach, aimed at creating a value through the algorithmization of company operations. We determine that social networks are one of the most important tools for digitalization of company's business processes, as they have a high organizational and management potential. We also systematize the effects of social media on company's business processes. Conclusions. We present theoretical provisions of the impact of social networks on business processes of enterprises, which will enable to model and organize ideas about the development of digital ecosystems and the formation of business models.

“I’m not a kid anymore!” Towards a teen-centric approach of online privacy management

MedienJournal ◽  
2020 ◽  
Vol 44 (1) ◽  
pp. 41-54
Author(s):  
Isabell Koinig
Keyword(s):  
Social Networks ◽  
Social Media ◽  
Present Article ◽  
Information Disclosure ◽  
Online Privacy ◽  
Privacy Management ◽  
Theoretical Contribution ◽  
Social Media Networks ◽  
Individual Privacy ◽  
Willingness To Disclose

The youth constitutes the largest user base of social media networks. While this generation has grown up in a digitally immersed environment, they are still not immune to the dangers the online space bears. Hence, maintaining their privacy is paramount. The present article presents a theoretical contribution, that is based on a review of relevant articles. It sets out to investigate the importance adolescents attribute to online privacy, which is likely to influence their willingness to disclose data. In line with a “new privacy paradox”, information disclosure is seen as unavoidable, given the centrality of social networks to adolescents’ lives. This goes hand in hand with individual privacy management. As individuals often lack knowledge as to how to protect their privacy, it is essential to educate the youth about their possibilities, equipping them with agency and self-responsibilization. This corresponds with a teen-centric approach to privacy as proposed by the TOSS framework.

Sign in / Sign up

Export Citation Format

Share Document