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

2021 ◽  
Vol 8 (9) ◽  
pp. 202245
Author(s):  
Ren-Meng Cao ◽  
Xiao Fan Liu ◽  
Xiao-Ke Xu
Keyword(s):  
Information Diffusion ◽  
Predictive Power ◽  
Diffusion Processes ◽  
Temporal Dynamics ◽  
Learning Algorithm ◽  
Short Term ◽  
Information Cascade ◽  
Term Prediction ◽  
Diffusion Dynamics

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.

scholarly journals A Novel Deep Learning Algorithm for Groundwater Level Prediction based on Spatiotemporal Attention Mechanism

2020 ◽  
Author(s):  
Chong Chen ◽  
Han Zhou ◽  
Hui Zhang ◽  
Lulu Chen ◽  
Zhu Yan ◽  
...  
Keyword(s):  
Deep Learning ◽  
Groundwater Level ◽  
Learning Algorithm ◽  
Attention Mechanism ◽  
Short Term ◽  
Groundwater Levels ◽  
Deep Learning Algorithm ◽  
Term Prediction ◽  
Groundwater Level Prediction

Abstract Groundwater resources play a vital role in production, human life and economic development. Effective prediction of groundwater levels would support better water resources management. Although machine learning algorithms have been studied and applied in many domains with good enough results, the researches in hydrologic domains are not adequate. This paper proposes a novel deep learning algorithm for groundwater level prediction based on spatiotemporal attention mechanism. Short-term (one month ahead) and long-term (twelve months ahead) prediction of groundwater level are conducted with observed groundwater levels collected from several boreholes in the middle reaches of the Heihe River Basin in northwestern China. Mean Absolute Error (MAE) and Root Mean Square Error (RMSE) are used to evaluate the performance of the proposed algorithm and several baseline models (i.e., SVR, Support Vector Regression; FNN, Feedforward Neural Networks; LSTM, Long Short-Term Memory neural network). The results show that the proposed model can effectively improve the prediction accuracy compared to the baseline models with MAE of 0.0754, RMSE of 0.0952 for short-term prediction and MAE of 0.0983, RMSE of 0.1215 for long-term prediction. This study provides a feasible and accurate approach for groundwater prediction which may facilitate decision making for water management.

Economic conditions and perceptions of immigrants as an economic threat in Europe: Temporal dynamics and mediating processes

2021 ◽  
pp. 002071522199352
Author(s):  
Boris Heizmann ◽  
Nora Huth
Keyword(s):  
Temporal Dynamics ◽  
European Social Survey ◽  
Primary Objective ◽  
Conflict Theory ◽  
Economic Conditions ◽  
Political Climate ◽  
Short Term ◽  
Economic Threat ◽  
Party Positions

This article addresses the extent to which economic downturns influence the perception of immigrants as an economic threat and through which channels this occurs. Our primary objective is an investigation of the specific mechanisms that connect economic conditions to the perception of immigrants as a threat. We therefore also contribute to theoretical discussions based on group threat and realistic group conflict theory by exposing the dominant source of competition relevant to these relationships. Furthermore, we investigate whether people react more sensitive to short-term economic dynamics within countries than to the long-term economic circumstances. Our database comprises all waves of the European Social Survey from 2002 to 2017. The macro-economic indicators we use include GDP per capita, unemployment, and national debt levels, covering the most salient economic dimensions. We furthermore control for the country’s migration situation and aggregate party positions toward cultural diversity. Our results show that the dynamic short-term developments of the economy and migration within countries are of greater relevance for perceived immigrant threat than the long-term situation. In contrast, the long-term political climate appears to be more important than short-term changes in the aggregate party positions. Further mediation analyses show that objective economic conditions influence anti-immigrant attitudes primarily through individual perceptions of the country’s economic performance and that unemployment rates are of primary importance.

scholarly journals Novel robust time series analysis for long-term and short-term prediction

2021 ◽  
Vol 11 (1) ◽  
Author(s):  
Hiroshi Okamura ◽  
Yutaka Osada ◽  
Shota Nishijima ◽  
Shinto Eguchi
Keyword(s):  
Robust Regression ◽  
Simulated Data ◽  
New Method ◽  
Short Term ◽  
Least Absolute Deviations ◽  
Term Prediction ◽  
Regression Approach ◽  
Short Term Prediction ◽  
Long Term Prediction

AbstractNonlinear phenomena are universal in ecology. However, their inference and prediction are generally difficult because of autocorrelation and outliers. A traditional least squares method for parameter estimation is capable of improving short-term prediction by estimating autocorrelation, whereas it has weakness to outliers and consequently worse long-term prediction. In contrast, a traditional robust regression approach, such as the least absolute deviations method, alleviates the influence of outliers and has potentially better long-term prediction, whereas it makes accurately estimating autocorrelation difficult and possibly leads to worse short-term prediction. We propose a new robust regression approach that estimates autocorrelation accurately and reduces the influence of outliers. We then compare the new method with the conventional least squares and least absolute deviations methods by using simulated data and real ecological data. Simulations and analysis of real data demonstrate that the new method generally has better long-term and short-term prediction ability for nonlinear estimation problems using spawner–recruitment data. The new method provides nearly unbiased autocorrelation even for highly contaminated simulated data with extreme outliers, whereas other methods fail to estimate autocorrelation accurately.

scholarly journals Uncovering the structure and temporal dynamics of information propagation

2014 ◽  
Vol 2 (1) ◽  
pp. 26-65 ◽  
Author(s):  
MANUEL GOMEZ RODRIGUEZ ◽  
JURE LESKOVEC ◽  
DAVID BALDUZZI ◽  
BERNHARD SCHÖLKOPF
Keyword(s):  
News Media ◽  
Information Diffusion ◽  
Large Scale ◽  
Temporal Dynamics ◽  
Inference Algorithm ◽  
Information Propagation ◽  
Transmission Rates ◽  
Diffusion Dynamics ◽  
Underlying Network ◽  
News Events

AbstractTime plays an essential role in the diffusion of information, influence, and disease over networks. In many cases we can only observe when a node is activated by a contagion—when a node learns about a piece of information, makes a decision, adopts a new behavior, or becomes infected with a disease. However, the underlying network connectivity and transmission rates between nodes are unknown. Inferring the underlying diffusion dynamics is important because it leads to new insights and enables forecasting, as well as influencing or containing information propagation. In this paper we model diffusion as a continuous temporal process occurring at different rates over a latent, unobserved network that may change over time. Given information diffusion data, we infer the edges and dynamics of the underlying network. Our model naturally imposes sparse solutions and requires no parameter tuning. We develop an efficient inference algorithm that uses stochastic convex optimization to compute online estimates of the edges and transmission rates. We evaluate our method by tracking information diffusion among 3.3 million mainstream media sites and blogs, and experiment with more than 179 million different instances of information spreading over the network in a one-year period. We apply our network inference algorithm to the top 5,000 media sites and blogs and report several interesting observations. First, information pathways for general recurrent topics are more stable across time than for on-going news events. Second, clusters of news media sites and blogs often emerge and vanish in a matter of days for on-going news events. Finally, major events, for example, large scale civil unrest as in the Libyan civil war or Syrian uprising, increase the number of information pathways among blogs, and also increase the network centrality of blogs and social media sites.

Information Diffusion in Social Networks

2011 ◽  
pp. 146-163 ◽  
Author(s):  
Dmitry Zinoviev
Keyword(s):  
Social Networks ◽  
Information Flow ◽  
Online Social Networks ◽  
Information Diffusion ◽  
Diffusion Processes ◽  
Small World ◽  
The Social ◽  
Strength Of Weak Ties ◽  
Strategic Position

The issue of information diffusion in small-world social networks was first systematically brought to light by Mark Granovetter in his seminal paper “The Strength of Weak Ties” in 1973 and has been an area of active academic studies in the past three decades. This chapter discusses information proliferation mechanisms in massive online social networks (MOSN). In particular, the following aspects of information diffusion processes are addressed: the role and the strategic position of influential spreaders of information; the pathways in the social networks that serve as conduits for communication and information flow; mathematical models describing proliferation processes; short-term and long-term dynamics of information diffusion, and secrecy of information diffusion.

The Research of Statistic Prediction for Wave Loads Based on Three Dimensional Method

2013 ◽  
Author(s):  
Yihan Zhang ◽  
Huilong Ren ◽  
Hui Li ◽  
Xiaoyu Li
Keyword(s):  
Structural Strength ◽  
Wave Spectrum ◽  
Three Dimensional ◽  
Frequency Interval ◽  
Wave Loads ◽  
Short Term ◽  
Empirical Formulas ◽  
Strength Assessment ◽  
Term Prediction

The exact prediction of wave loads for ship or other marine structure is the key to its design and the assessment of structural strength, reliability and security. The short-term and long-term prediction of wave loads are always used in direct calculation for structural strength, fatigue strength assessment and so on based on spectral analysis method. In this paper, the numerical calculation method for statistic prediction is discussed firstly, including the Weibull distribution fitted method and the stack method. Further more, it is necessary to find a quick solution in order to improve the efficiency to compute the nonlinear equation in the second method. Then, some main factors that may influence the long-term or short-term prediction are discussed, such as wave spectrum, wave scatter diagram, incident wave angle interval and frequency interval. Finally, the wave loads prediction for a series of typical bulk carriers and oil tankers are calculated by the uniform predict method discussed above base on three dimensional wave loads calculation theory. The results showed that the method used in this paper can predict the statistic value of wave loads induced by irregular incident waves conveniently and efficiently. A rule to choose a series of uniform factors is confirmed for statistic prediction and some empirical formulas for long-term value of wave bending moment are concluded which are very useful in marine engineering.

scholarly journals The Dimension of Time in Host-Microbiome Interactions

mSystems ◽  
2019 ◽  
Vol 4 (1) ◽  
Author(s):  
Giulia T. Uhr ◽  
Lenka Dohnalová ◽  
Christoph A. Thaiss
Keyword(s):  
Microbial Community ◽  
Environmental Factors ◽  
Temporal Dynamics ◽  
Therapeutic Strategies ◽  
Intestinal Microbiome ◽  
Short Term ◽  
Intestinal Microbial Community ◽  
Intermediate States ◽  
Different Time Scales

ABSTRACT The intestinal microbiota contains trillions of commensal microorganisms that shape multiple aspects of host physiology and disease. In contrast to the host’s genome, the microbiome is amenable to change over the course of an organism’s lifetime, providing an opportunity to therapeutically modulate the microbiome’s impact on human pathophysiology. In this Perspective, we highlight environmental factors that regulate the temporal dynamics of the intestinal microbiome, with a particular focus on the different time scales at which they act. We propose that the identification of transient and intermediate states of microbiome responses to perturbations is essential for understanding the rules that govern the behavior of this ecosystem. The delineation of microbiome dynamics is also helpful for distinguishing cause and effect in microbiome responses to environmental stimuli. Understanding the dimension of time in host-microbiome interactions is therefore critical for therapeutic strategies that aim at short-term or long-term engineering of the intestinal microbial community.

scholarly journals On Retrospecting Human Dynamics with Attention

2019 ◽  
Author(s):  
Minjing Dong ◽  
Chang Xu
Keyword(s):  
Human Motion ◽  
Motion Prediction ◽  
Sufficient Information ◽  
Short Term ◽  
Human Dynamics ◽  
Time Horizons ◽  
Term Prediction ◽  
Error Accumulation ◽  
Short Term Prediction

Deep recurrent neural networks have achieved impressive success in forecasting human motion with a sequence to sequence architecture. However, forecasting in longer time horizons often leads to implausible human poses or converges to mean poses, because of error accumulation and difficulties in keeping track of longerterm information. To address these challenges, we propose to retrospect human dynamics with attention. A retrospection module is designed upon RNN to regularly retrospect past frames and correct mistakes in time. This significantly improves the memory of RNN and provides sufficient information for the decoder networks to generate longer term prediction. Moreover, we present a spatial attention module to explore and exploit cooperation among joints in performing a particular motion. Residual connections are also included to guarantee the performance of short term prediction. We evaluate the proposed algorithm on the largest and most challenging Human 3.6M dataset in the field. Experimental results demonstrate the necessity of investigating motion prediction in a self audit manner and the effectiveness of the proposed algorithm in both short term and long term predictions.

Sign in / Sign up

Export Citation Format

Share Document