Predicting Information Diffusion Research Articles

TRGCN: A Prediction Model for Information Diffusion Based on Transformer and Relational Graph Convolutional Network

In order to capture and integrate the structural features and temporal features contained in social graph and diffusion cascade more effectively, an information diffusion prediction model based on the Transformer and Relational Graph Convolutional Network (TRGCN) is proposed. Firstly, a dynamic heterogeneous graph composed of the social network graph and the diffusion cascade graph was constructed, and it was input into the Relational Graph Convolutional Network (RGCN) to extract the structural features of each node. Secondly, the time embedding of each node was reencoded using Bi-directional Long Short-Term Memory (Bi-LSTM). The time decay function was introduced to give different weights to nodes at different time positions, so as to obtain the temporal features of nodes. Finally, structural features and temporal features were input into Transformer and then merged. The spatiotemporal features are obtained for information diffusion prediction. The experimental results on three real datasets of X (formerly known as Twitter), Douban, and Memetracker show that compared with the optimal model in the comparison experiment, the TRGCN model has an average increase of 4.16% in Hits@100 metric and 13.26% in map@100 metric. The validity and rationality of the model are proved.

Decoupling User Relationships Guides Information Diffusion Prediction (Student Abstract)

Information diffusion prediction is a critical task for many social network applications. However, current methods are mainly limited by the following aspects: user relationships behind resharing behaviors are complex and entangled. To address these issues, we propose MHGFormer, a novel multi-channel hypergraph transformer framework, to better decouple complex user relations and obtain fine-grained user representations. First, we employ designed triangular motifs to decouple user relations into three different level hypergraphs. Second, a position-aware hypergraph transformer is used to refine user relation and obtain high-quality user representations. Extensive experiments conducted on two social datasets demonstrate that MHGFormer outperforms state-of-the-art diffusion models across several settings.

Enhancing Multi-Scale Diffusion Prediction via Sequential Hypergraphs and Adversarial Learning

Information diffusion prediction plays a crucial role in understanding the propagation of information in social networks, encompassing both macroscopic and microscopic prediction tasks. Macroscopic prediction estimates the overall impact of information diffusion, while microscopic prediction focuses on identifying the next user to be influenced. While prior research often concentrates on one of these aspects, a few tackle both concurrently. These two tasks provide complementary insights into the diffusion process at different levels, revealing common traits and unique attributes. The exploration of leveraging common features across these tasks to enhance information prediction remains an underexplored avenue. In this paper, we propose an intuitive and effective model that addresses both macroscopic and microscopic prediction tasks. Our approach considers the interactions and dynamics among cascades at the macro level and incorporates the social homophily of users in social networks at the micro level. Additionally, we introduce adversarial training and orthogonality constraints to ensure the integrity of shared features. Experimental results on four datasets demonstrate that our model significantly outperforms state-of-the-art methods.

GRASS: Learning Spatial-Temporal Properties From Chainlike Cascade Data for Microscopic Diffusion Prediction.

Information diffusion prediction captures diffusion dynamics of online messages in social networks. Thus, it is the basis of many essential tasks such as popularity prediction and viral marketing. However, there are two thorny problems caused by the loss of spatial-temporal properties of cascade data: "position-hopping" and "branch-independency." The former means no exact propagation relationship between any two consecutive infected users. The latter indicates that not all previously infected users contribute to the prediction of the next infected user. This article proposes the GRU-like Attention Unit and Structural Spreading (GRASS) model for microscopic cascade prediction to overcome the above two problems. First, we introduce the attention mechanism into the gated recurrent unit (GRU) component to expand the restricted receptive field of the recurrent neural network (RNN)-type module, thus addressing the "position-hopping" problem. Second, the structural spreading (SS) mechanism leverages structural features to filter out related users and controls the generation of cascade hidden states, thereby solving the "branch-independency" problem. Experiments on multiple real-world datasets show that our model significantly outperforms state-of-the-art baseline models on both hits@κ and map@κ metrics. Furthermore, the visualization of latent representations by t-distributed stochastic neighbor embedding (t-SNE) indicates that our model makes different cascades more discriminative during the encoding process.

Extracting the diffusion dynamics of crisis information on online social networks: Model and application

Disaster mitigation greatly benefits from the diffusion of crisis information. To learn about the diffusion dynamics of crisis information on online social networks, this paper puts forward a crisis information diffusion model based on population dynamics and further analyses its parameters, such as ordinary users’ average number of followers, the number of potential audience members who might spread the crisis information, the forwarding probability for each audience member and the attenuation speed of the information based on real data from Sina Weibo. In addition, a method for the prediction of crisis information diffusion is proposed and verified on the basis of this model. The results show that this model could describe and predict well the diffusion process of crisis information on online social networks, enabling relevant departments to develop appropriate strategies for crisis information diffusion.

A novel regularized weighted estimation method for information diffusion prediction in social networks

In recent years, social networks have become popular among Internet users, and various studies have been performed on the analysis of users’ behavior in social networks. Information diffusion analysis is one of the leading fields in social network analysis. In this context, users are influenced by other users in the social network, such as their friends. User behavior is analyzed using several models designed for information diffusion modeling and prediction. In this paper, first, the problem of estimating the diffusion probabilities for the independent cascade model is studied. We propose a method for estimating diffusion probabilities. This method assigns a weight to each individual diffusion sample within a network. To account for the different effects of diffusion samples, several weighting schemes are proposed. Afterward, the proposed method is applied to real cascade datasets such as Twitter and Digg. We try to estimate diffusion probabilities for the independent cascade model considering the continuous time of nodes’ infections. The results of our evaluation of our methods are presented based on several datasets. The results show the high performance of our methods in terms of training time as well as other metrics such as mean absolute error and F-measure.

A cascade information diffusion prediction model integrating topic features and cross-attention

Information cascade prediction is a crucial task in social network analysis. However, previous research has only focused on the impact of social relationships on cascade information diffusion, while ignoring the differences caused by the characteristics of cascade information itself, which limits the performance of prediction results. We propose a novel cascade information diffusion prediction model (Topic-HGAT). Firstly, we extract features from different topic features to enhance the learned cascade information representation. To better implement this method, we use hypergraphs to better characterize cascade information and dynamically learn multiple diffusion sub-hypergraphs according to the time process; secondly, we introduce cross-attention mechanisms to learn each other's feature representations from the perspectives of both user representation and cascade representation, thereby achieving deep fusion of the two features. This solves the problem of poor feature fusion effect caused by simply calculating self-attention on learned user representation and cascade representation in previous studies; finally, we conduct comparative experiments on four real datasets, including Twitter and Douban. Experimental results show that the proposed Topic-HGAT model achieves the highest improvements of 2.91% and 1.59% on Hits@100 and MAP@100 indicators, respectively, compared to other 8 baseline models, verifying the rationality and effectiveness of the proposed Topic-HGAT model.

An Extension of the Susceptible–Infected Model and Its Application to the Analysis of Information Dissemination in Social Networks

Social media significantly influences business, politics, and society. Easy access and interaction among users allow information to spread rapidly across social networks. Understanding how information is disseminated through these new publishing methods is crucial for political and marketing purposes. However, modeling and predicting information diffusion is challenging due to the complex interactions between network users. This study proposes an analytical approach based on diffusion models to predict the number of social media users engaging in discussions on a topic. We develop a modified version of the susceptible–infected (SI) model that considers the heterogeneity of interactions between users in complex networks. Our model considers the network structure, abandons the assumption of homogeneous mixing, and focuses on information diffusion in scale-free networks. We provide explicit algorithms for modeling information propagation on different types of random graphs and real network structures. We compare our model with alternative approaches, both those considering network structure and those that do not. The accuracy of our model in predicting the number of informed nodes in simulated information diffusion networks demonstrates its effectiveness in describing and predicting information dissemination in social networks. This study highlights the potential of graph-based epidemic models in analyzing online discussion topics and understanding other phenomena spreading on social networks.

H-Diffu: Hyperbolic Representations for Information Diffusion Prediction

With the proliferation of online social networks, a great deal of online user action data has been generated. Such data has enabled the study of information diffusion prediction, which is a fundamental problem for understanding the propagation of information on social media platforms. In diffusion prediction models, there are two standard components, i.e., a social graph and information diffusion cascades. We observe that both components exhibit latent hierarchical structures. However, most existing models are designed based on Euclidean spaces, and hence cannot effectively capture complex patterns, especially hierarchical structures. Therefore, we investigate a novel research problem to learn hyperbolic representations for information diffusion prediction. To reflect the different characteristics of social graphs and diffusion cascades, we encode them into two latent hyperbolic spaces with different trainable curvatures. In addition, to model influence dependencies, we propose a co-attention mechanism to capture the processes of diffusion cascades using positional embeddings. Given a set of activated seed users, we jointly exploit diffusion cascades and social links to predict which users will be influenced. We conduct extensive experiments on four real-world datasets. Empirical results demonstrate that the proposed H-Diffu model significantly outperforms several state-of-the-art diffusion prediction frameworks.

CasTformer: A novel cascade transformer towards predicting information diffusion

Predicting information diffusion cascade is an essential task in social networks. We mainly focus on predicting the size of the information cascade. The relationships inside a cascade are diverse, including global and relative spatio-temporal relationships, as well as interpersonal influence relationships. These complex relationships between nodes play a crucial role in cascade prediction, but they have not been thoroughly investigated. The Transformer's global receptive field can assist in capturing the relationships between two arbitrary nodes. However, using Transformer directly for a cascade is insufficient without considering its temporal and structural characteristics. In this paper, we propose a novel cascade Transformer for the first time, called CasTformer, specifically designed for cascade size prediction. CasTformer utilizes a global spatio-temporal positional encoding and relative relationship bias matrices on the self-attention mechanism to capture diverse cascade relationships. Moreover, self-knowledge distillation is employed for obtaining a better cascade representation to enhance prediction performance. We use four datasets with nearly millions of cascade samples to validate our model and it achieves training in 3 hours. Experimental results show that it outperforms state-of-the-art methods by an average of 11.9%, 6.1%, and 9.6% on MSLE, MAPE, and R2, respectively.

Information diffusion prediction based on cascade sequences and social topology

People have been increasingly sharing information via social media platforms such as Twitter and Facebook in recent years, making understanding and predicting the spread of information a hot research topic. Accurate prediction of cascades within social platforms can effectively track the information dissemination process and prevent the spread of harmful information. Previous work either did not fully exploit the potential social graph structure or chose to predict communication sequences as a diffusion graph, resulting in inconsistency with the actual diffusion situation. We propose a method that is structurally simple and effective, requiring only sequential sequences of users' spread information and social relationships among users. Our method is based on LSTM (Long Short-Term Memory) for temporal feature extraction of cascade sequences and combined with GCN (Graph Convolutional Networks) for extracting features containing node topology in social graphs for microscopic prediction of information diffusion cascades. Comparative experiments on two real social platform datasets demonstrate that our method has a better prediction effect.

Prediction of Information Diffusion of New Products: Based on Product Launch and Media Difference

Prediction of Information Diffusion of New Products: Based on Product Launch and Media Difference

Full-Scale Information Diffusion Prediction With Reinforced Recurrent Networks.

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 who will be the next influenced user at what time, or macroscopic diffusion prediction, which estimates the total numbers of influenced users during the diffusion process. To the best of our knowledge, few attempts have been made to suggest a unified model for both microscopic and macroscopic scales. In this article, we propose a novel full-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 nondifferentiable 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.

Relation-enhanced Diffusion Model with LightGCN for Information Diffusion Prediction

Modeling and predicting the information diffusion process on social platforms is a critical task in many real-world applications. Recent studies generally model the diffusion graph using graph neural networks to capture the implicit dependencies among users. However, existing studies construct the diffusion graph in a way which cannot fully describe the global dependencies of users due to their narrow definition of user relationship. Meanwhile, graph neural networks in these methods are not suitable for the social network scenario which has scarce node attributes. Therefore, we propose a novel diffusion graph construction method which can enhance relations among users and adopt a simplified graph convolutional operation which is suitable for diffusion prediction scenario. The learned user embedding in our model can effectively preserve the microscopic structure and the high-order proximities between users lies in both the social graph and diffusion graph. Experimental results on four real-world datasets show that the proposed model is superior to the most advanced information diffusion prediction methods.

Path prediction of information diffusion based on a topic-oriented relationship strength network

Path prediction of information diffusion is helpful for early warning and monitoring of network public opinion. Previous research focused on collecting feature sets to predict netizens’ spreading behavior, and few of them went further into predicting information diffusion path cascade by cascade. To solve this problem effectively, we proposed a prediction method based on a topic-oriented relationship strength network. First, we analyzed a subset of historical interaction records and found the temporal correlations in interactive frequency and in interest topics between users. Second, we constructed a topic-oriented relationship strength network to indicate users’ spreading preferences, including frequency and interest. Third, we collected some features and applied machine learning models to predict information diffusion paths cascade by cascade in the network. The experimental results testified that our method could predict the information diffusion path effectively with fewer features. Moreover, our experimental network shows some interest communities and different roles of users in information diffusion.

Predicting opinion evolution based on information diffusion in social networks using a hybrid fuzzy based approach.

Social media plays an important role in disseminating information and analysing public and government opinions. The vast majority of previous research has examined information diffusion and opinion analysis separately. This study proposes a new framework for analysing both information diffusion and opinion evolution. The change in opinion over time is known as opinion evolution. To propose a new model for predicting information diffusion and opinion analysis in social media, a forest fire algorithm, cuckoo search, and fuzzy c-means clustering are used. The forest fire algorithm is used to determine the diffuser and non-diffuser of information in social networks, and fuzzy c-means clustering with the cuckoo search optimization algorithm is proposed to cluster Twitter content into various opinion categories and to determine opinion change. On different Twitter data sets, the proposed model outperformed the existing methods in terms of precision, recall, and accuracy.

UAV-Aided Information Diffusion for Vehicle-to-Vehicle (V2V) in Disaster Scenarios

To support safe driving and automatic operation, collecting and providing information are important in intelligent transport systems (ITSs). Information and communication technology utilization is needed even when disasters occur because it is possible to collect and analyze vehicle position information via roadside units and thus locate accidents and traffic jams. However, if the roadside units are damaged by disasters or power outages, these functions cannot be provided. Therefore, we consider ITS function assistance using unmanned aerial vehicles (UAVs), which can spread information without being affected by the availability of roads and traffic congestion. Simply flying UAVs without a plan will cause problems such as delays due to unnecessary movement and information transmission to areas where vehicles do not exist. Therefore, we propose a method for predicting information diffusion by vehicle-to-vehicle communication to control the flight trajectory of UAVs, with the aim of quickly spreading information to many vehicles. To predict information diffusion, we use a reaction-diffusion model, which is a partial differential equation, and construct a model that considers the effects of vehicle-to-vehicle communication. The effectiveness of the proposed method is evaluated through the simulation, and the results show that the method performs better than the comparison methods.

MS-HGAT: Memory-Enhanced Sequential Hypergraph Attention Network for Information Diffusion Prediction

Predicting the diffusion cascades is a critical task to understand information spread on social networks. Previous methods usually focus on the order or structure of the infected users in a single cascade, thus ignoring the global dependencies of users and cascades, limiting the performance of prediction. Current strategies to introduce social networks only learn the social homogeneity among users, which is not enough to describe their interaction preferences, let alone the dynamic changes. To address the above issues, we propose a novel information diffusion prediction model named Memory-enhanced Sequential Hypergraph Attention Networks (MS-HGAT). Specifically, to introduce the global dependencies of users, we not only take advantages of their friendships, but also consider their interactions at the cascade level. Furthermore, to dynamically capture user' preferences, we divide the diffusion hypergraph into several sub graphs based on timestamps, develop Hypergraph Attention Networks to learn the sequential hypergraphs, and connect them with gated fusion strategy. In addition, a memory-enhanced embedding lookup module is proposed to capture the learned user representations into the cascade-specific embedding space, thus highlighting the feature interaction within the cascade. The experimental results over four realistic datasets demonstrate that MS-HGAT significantly outperforms the state-of-the-art diffusion prediction models in both Hits@K and MAP@k metrics.

Understanding information diffusion with psychological field dynamic

Several approaches focus on how to automatically capture the latent features from original diffusion data and predict the future scale of cascades utilizing a black box framework. However, they ignore the penetrating insight into the underlying mechanism that how each participant is involved in the cascade. In this work, we bridge the gap between prediction and understanding of information diffusion by incorporating deep learning techniques and social psychology. To characterize individual participation driven by both subjective and objective impetus and integrate it into the macro-level cascade, we propose an end-to-end model, named PFDID, which is designed based on the field dynamics theory of psychology, including the intrinsic cognition field and the extrinsic environment field. We represent these two field dynamics respectively with the pairwise semantic relation between the message itself and corresponding comment and the forwarder’s micro-community activity embedding to provide educated explanations for forwarding behaviour. Afterwards, the cross infusion mechanism is designed to calculate the mutual influence of inhomogeneous field dynamics inside users and cross influence of homogeneous field dynamics among individuals, whose output is fed into the diffusion network aggregation layer for the cascade size prediction. Extensive experiments on two typical social networks, Sina Weibo and Twitter, manifest that the proposed PFDID outperforms state-of-the-art approaches. Our model achieves excellent prediction results, with MSLE = 1.856 on Sina Weibo and MSLE = 1.962 on Twitter, providing 6.54% and 10.53% relative performance gains, respectively. Furthermore, the interpretability is also discussed based on detailed visualization. We observe that the psychological impetus behind social behaviour varies mainly following two patterns with the spread of information, including gradual change and joint influence. Additionally, the indirect dependencies have also been verified.

Joint Learning of User Representation With Diffusion Sequence and Network Structure

Information sharing behavior and social link building behavior have shown strong correlation on social media. The aim of this paper is to explore this correlation for simultaneously modeling and predicting sharing behavior in information diffusion sequences and linking behavior in social network, which correspond to information diffusion prediction and social link prediction problems. To achieve this goal, we propose a joint user representation learning model to characterize the two correlated behaviors in a shared latent space. The proposed model learns user representations via two maximum likelihood estimation objectives defined on observed information diffusion sequences and social network structure respectively and incorporates them in a unified framework. A multi-task learning algorithm is designed for efficient model optimization. Based on the learned representations, the model can be directly applied to predicting diffusion processes and inferring unobserved social links at the same time. We evaluate the proposed model on two real social media datasets with extensive experiments. The model consistently achieves significant improvements over the state-of-the-art approaches on diffusion prediction and link prediction tasks. The better robustness of our model in further ablation studies demonstrates that capturing the behavior correlation in the shared representation space is beneficial.