scholarly journals A novel information diffusion model based on psychosocial factors with automatic parameter learning

2020 ◽  
pp. 50-50
Author(s):  
Sabina-Adriana Floria ◽  
Florin Leon
Keyword(s):  
Online Social Networks ◽  
Information Diffusion ◽  
Gregarious Behavior ◽  
Proposed Model ◽  
Transmission Of Information ◽  
Two Factors ◽  
Information Diffusion Model ◽  
Real World Datasets ◽  
Sociological Factor ◽  
Novel Model

Online social networks are the main choice of people to maintain their social relationships and share information or opinions. Estimating the actions of a user is not trivial because an individual can act spontaneously or be influenced by external factors. In this paper we propose a novel model for imitating the evolution of the information diffusion in a network as well as possible. Each individual is modeled as a node with two factors (psychological and sociological) that control its probabilistic transmission of information. The psychological factor refers to the node?s preference for the topic discussed, i.e. the information diffused. The sociological factor takes into account the influence of the neighbors? activity on the node, i.e. the gregarious behavior. A genetic algorithm is used to automatically tune the parameters of the model in order to fit the evolution of information diffusion observed in two real-world datasets with three topics. The reproduced diffusions show that the proposed model imitates the real diffusions very well.

scholarly journals Multi-scale Information Diffusion Prediction with Reinforced Recurrent Networks

2019 ◽  
Author(s):  
Cheng Yang ◽  
Jian Tang ◽  
Maosong Sun ◽  
Ganqu Cui ◽  
Zhiyuan Liu
Keyword(s):  
Information Diffusion ◽  
State Of The Art ◽  
Sequential Data ◽  
Recurrent Networks ◽  
Multi Scale ◽  
Structural Context ◽  
Learning Techniques ◽  
Proposed Model ◽  
Real World Datasets ◽  
Diffusion Prediction

Information diffusion prediction is an important task which studies how information items spread among users. With the success of deep learning techniques, recurrent neural networks (RNNs) have shown their powerful capability in modeling information diffusion as sequential data. However, previous works focused on either microscopic diffusion prediction which aims at guessing the next influenced user or macroscopic diffusion prediction which estimates the total numbers of influenced users during the diffusion process. To the best of our knowledge, no previous works have suggested a unified model for both microscopic and macroscopic scales. In this paper, we propose a novel multi-scale diffusion prediction model based on reinforcement learning (RL). RL incorporates the macroscopic diffusion size information into the RNN-based microscopic diffusion model by addressing the non-differentiable problem. We also employ an effective structural context extraction strategy to utilize the underlying social graph information. Experimental results show that our proposed model outperforms state-of-the-art baseline models on both microscopic and macroscopic diffusion predictions on three real-world datasets.

scholarly journals Modeling the Information Diffusion of Overlapped Nodes using SFA-ICBDM

2019 ◽  
Vol 8 (2) ◽  
pp. 709-713
Keyword(s):  
Social Networks ◽  
Online Social Networks ◽  
Information Diffusion ◽  
Cascade Model ◽  
Recent Time ◽  
Rumor Spreading ◽  
Overlapping Communities ◽  
Network Diversity ◽  
Proposed Model ◽  
Almost All

:In recent time, online social networks like, Facebook, Twitter, and other platforms, provide functionality that allows a chunk of information migrates from one user to another over a network. Almost all the actual networks exhibit the concept of community structure. Indeed overlapping communities are very common in a complex network such as online social networks since nodes could belong to multiple communities at once. The huge size of the real-world network, diversity in users profiles and, the uncertainty in their behaviors have made modeling the information diffusion in such networks to become more and more complex and tend to be less accurate. This work pays much attention on how we can accurately predicting information diffusion cascades over social networks taking into account the role played by the overlapping nodes in the diffusion process due to its belonging to more than one community. According to that, the information diffusion is modeled in communities in which these nodes have high membership for reasons that may relate to the applications such as market optimization and rumor spreading. Our experiment made on a real social data, Digg news aggregator network on 15% of overlapped nodes, using our proposed model SFA-ICBDM described in previous work. The experimental results show that the cascade model of the overlapped nodes whether represents seed or node within cascade achieves best prediction accuracy in the community which the node belongs at more

Jointly Modeling Spatio–Temporal Dependencies and Daily Flow Correlations for Crowd Flow Prediction

2021 ◽  
Vol 15 (4) ◽  
pp. 1-20
Author(s):  
Tianzi Zang ◽  
Yanmin Zhu ◽  
Yanan Xu ◽  
Jiadi Yu
Keyword(s):  
Traffic Management ◽  
Intelligent Transportation System ◽  
System Construction ◽  
Strong Correlations ◽  
Flow Prediction ◽  
Proposed Model ◽  
Spatio Temporal ◽  
Real World Datasets ◽  
Novel Model ◽  
Temporal Dependencies

Crowd flow prediction is a vital problem for an intelligent transportation system construction in a smart city. It plays a crucial role in traffic management and behavioral analysis, thus it has raised great attention from many researchers. However, predicting crowd flows timely and accurately is a challenging task that is affected by many complex factors such as the dependencies of adjacent regions or recent crowd flows. Existing models mainly focus on capturing such dependencies in spatial or temporal domains and fail to model relations between crowd flows of distant regions. We notice that each region has a relatively fixed daily flow and some regions (even very far away from each other) may share similar flow patterns which show strong correlations among them. In this article, we propose a novel model named Double-Encoder which follows a general encoder–decoder framework for multi-step citywide crowd flow prediction. The model consists of two encoder modules named ST-Encoder and FR-Encoder to model spatial-temporal dependencies and daily flow correlations, respectively. We conduct extensive experiments on two real-world datasets to evaluate the performance of the proposed model and show that our model consistently outperforms state-of-the-art methods.

scholarly journals HID: Hierarchical Multiscale Representation Learning for Information Diffusion

2020 ◽  
Author(s):  
Honglu Zhou ◽  
Shuyuan Xu ◽  
Zuohui Fu ◽  
Gerard de Melo ◽  
Yongfeng Zhang ◽  
...  
Keyword(s):  
Multiscale Modeling ◽  
Online Social Networks ◽  
Information Diffusion ◽  
Representation Learning ◽  
Complex Interactions ◽  
Learning Tasks ◽  
Current State ◽  
Real World Datasets ◽  
Vector Representations ◽  
Hierarchical Multiscale

Multiscale modeling has yielded immense success on various machine learning tasks. However, it has not been properly explored for the prominent task of information diffusion, which aims to understand how information propagates along users in online social networks. For a specific user, whether and when to adopt a piece of information propagated from another user is affected by complex interactions, and thus, is very challenging to model. Current state-of-the-art techniques invoke deep neural models with vector representations of users. In this paper, we present a Hierarchical Information Diffusion (HID) framework by integrating user representation learning and multiscale modeling. The proposed framework can be layered on top of all information diffusion techniques that leverage user representations, so as to boost the predictive power and learning efficiency of the original technique. Extensive experiments on three real-world datasets showcase the superiority of our method.

A mean-field-theoretic model for dual information propagation in networks

2019 ◽  
Vol 7 (4) ◽  
pp. 585-602
Author(s):  
Utkarsh Niranjan ◽  
Anurag Singh ◽  
Ramesh Kumar Agrawal
Keyword(s):  
Information Diffusion ◽  
Information Source ◽  
Mean Field ◽  
Spreading Rate ◽  
Theoretic Model ◽  
Scale Free ◽  
Final Population ◽  
Proposed Model ◽  
Free Network ◽  
Novel Model

Abstract The Internet is a place where a vast amount of information is flowing. With the deeper penetration of social media, everybody is participating in spreading information. Often we find ourselves confused with competing information on the same topic. In this work, we present a novel model for competitive information diffusion on the scale-free network. The proposed model is an extension of the classical DK model of rumour spreading. Most of previous competitive information diffusion models consider a different type of stiflers to be similar. In our model we have two separate compartments for different types of stiflers. We present a detailed analysis about the effect of infection rate on the prevalence of rumour in the network. To capture the large chunk of population one requires relatively higher spreading rate. Relative impact of spreading rate and stifler rate on the final population in different compartments is also presented. In our analysis, we find that if stifler rate is higher than the spreading rate, a large portion of population remains unaware of rumours. We also find that if the information source is a popular person than people have a bias towards that information and information coming from less popular persons lose its grip on the network and lose the competition. This analysis illustrates that why big companies hire famous celebrities to promote their products. We also demonstrate rumour spreading analysis with numerical solution, network simulation and real network topology of Facebook.

Modelling information diffusion based on non-dominated friends in social networks

2016 ◽  
Vol 43 (6) ◽  
pp. 801-815 ◽  
Author(s):  
Niloofar Mozafari ◽  
Ali Hamzeh ◽  
Sattar Hashemi
Keyword(s):  
Social Networks ◽  
Social Network ◽  
Diffusion Model ◽  
Information Diffusion ◽  
Information Dissemination ◽  
Single Factor ◽  
Proposed Model ◽  
The Social ◽  
Diffusion Pattern ◽  
Information Diffusion Model

In recent years, social networks have played a strong role in diffusing information among people all around the globe. Therefore, the ability to analyse the diffusion pattern is essential. A diffusion model can identify the information dissemination pattern in a social network. One of the most important components of a diffusion model is information perception which determines the source each node receives its information from. Previous studies have assumed information perception to be just based on a single factor, that is, each individual receives information from their friend with the highest amount of information, whereas in reality, there exist other factors, such as trust, that affect the decision of people for selecting the friend who would supply information. These factors might be in conflict with each other, and modelling diffusion process with respect to a single factor can give rise to unacceptable results with respect to the other factors. In this article, we propose a novel information diffusion model based on non-dominated friends (IDNDF). Non-dominated friends are a set of friends of a node for whom there is no friend better than them in the set based on all considered factors, considering different factors simultaneously significantly enhance the proposed information diffusion model. Moreover, our model gives a chance to all non-dominated friends to be selected. Also, IDNDF allows having partial knowledge by each node of the social network. Finally, IDNDF is applicable to different types of data, including well-known real social networks like Epinions, WikiPedia, Advogato and so on. Extensive experiments are performed to assess the performance of the proposed model. The results show the efficiency of the IDNDF in diffusion of information in varieties of social networks.

Sign in / Sign up

Export Citation Format

Share Document