Dataset Information

Why cannot long-term cascade be predicted? Exploring temporal dynamics in information diffusion processes.

ABSTRACT: Predicting information cascade plays a crucial role in various applications such as advertising campaigns, emergency management and infodemic controlling. However, predicting the scale of an information cascade in the long-term could be difficult. In this study, we take Weibo, a Twitter-like online social platform, as an example, exhaustively extract predictive features from the data, and use a conventional machine learning algorithm to predict the information cascade scales. Specifically, we compare the predictive power (and the loss of it) of different categories of features in short-term and long-term prediction tasks. Among the features that describe the user following network, retweeting network, tweet content and early diffusion dynamics, we find that early diffusion dynamics are the most predictive ones in short-term prediction tasks but lose most of their predictive power in long-term tasks. In-depth analyses reveal two possible causes of such failure: the bursty nature of information diffusion and feature temporal drift over time. Our findings further enhance the comprehension of the information diffusion process and may assist in the control of such a process.

SUBMITTER: Cao RM

PROVIDER: S-EPMC8437228 | biostudies-literature | 2021 Sep

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Why cannot long-term cascade be predicted? Exploring temporal dynamics in information diffusion processes.

Cao Ren-Meng RM Liu Xiao Fan XF Xu Xiao-Ke XK

Royal Society open science 20210901 9

Predicting information cascade plays a crucial role in various applications such as advertising campaigns, emergency management and infodemic controlling. However, predicting the scale of an information cascade in the long-term could be difficult. In this study, we take Weibo, a Twitter-like online social platform, as an example, exhaustively extract predictive features from the data, and use a conventional machine learning algorithm to predict the information cascade scales. Specifically, we co ...[more]

PMID: 34540241

Similar Datasets

Project description:Progress has been made in understanding how temporal network features affect the percentage of nodes reached by an information diffusion process. In this work, we explore further: which node pairs are likely to contribute to the actual diffusion of information, i.e., appear in a diffusion trajectory? How is this likelihood related to the local temporal connection features of the node pair? Such deep understanding of the role of node pairs is crucial to tackle challenging optimization problems such as which kind of node pairs or temporal contacts should be stimulated in order to maximize the prevalence of information spreading. We start by using Susceptible-Infected (SI) model, in which an infected (information possessing) node could spread the information to a susceptible node with a given infection probability β whenever a contact happens between the two nodes, as the information diffusion process. We consider a large number of real-world temporal networks. First, we propose the construction of an information diffusion backbone GB(β) for a SI spreading process with an infection probability β on a temporal network. The backbone is a weighted network where the weight of each node pair indicates how likely the node pair appears in a diffusion trajectory starting from an arbitrary node. Second, we investigate the relation between the backbones with different infection probabilities on a temporal network. We find that the backbone topology obtained for low and high infection probabilities approach the backbone GB(β → 0) and GB(β = 1), respectively. The backbone GB(β → 0) equals the integrated weighted network, where the weight of a node pair counts the total number of contacts in between. Finally, we explore node pairs with what local connection features tend to appear in GB(β = 1), thus actually contribute to the global information diffusion. We discover that a local connection feature among many other features we proposed, could well identify the (high-weight) links in GB(β = 1). This local feature encodes the time that each contact occurs, pointing out the importance of temporal features in determining the role of node pairs in a dynamic process.

Project description:BackgroundDespite many studies on the importance of competition and plants' associations with mutualists and pathogens on plant performance and community organization, the joint effects of these two factors remain largely unexplored. Even less is known about how these joint effects vary through a plant's life in different environmental conditions and how they contribute to the long-term coexistence of species.MethodsWe investigated the role of plant-soil feedback (PSF) in intra- and interspecific competition, using two co-occurring dry grassland species as models. A two-phase PSF experiment was used. In the first phase, soil was conditioned by the two plant species. In the second, we assessed the effect of soil conditioning, competition and drought stress on seedling establishment, plant growth in the first and second vegetation season, and fruit production. We also estimated effects of different treatments on overall population growth rates and predicted the species' potential coexistence.ResultsSoil conditioning played a more important role in the early stages of the plants' life (seedling establishment and early growth) than competition. Specifically, we found strong negative intraspecific PSF for biomass production in the first year in both species. Although the effects of soil conditioning persisted in later stages of plant's life, competition and drought stress became more important. Surprisingly, models predicting species coexistence contrasted with the effects on individual life stages, showing that our model species benefit from their self-conditioned soil in the long run.ConclusionsWe provide evidence that the effects of PSF vary through plants' life stages. Our study suggests that we cannot easily predict the effects of soil conditioning on long-term coexistence of species using data only on performance at a single time as commonly done in PSF studies. We also show the importance of using as realistic environmental conditions as possible (such as drought stress experienced in dry grasslands) to draw reasonable conclusions on species coexistence.

Dataset Information

Why cannot long-term cascade be predicted? Exploring temporal dynamics in information diffusion processes.

Publications

Why cannot long-term cascade be predicted? Exploring temporal dynamics in information diffusion processes.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets