Social Diffusion Processes Research Articles

Context-Enhanced Probabilistic Diffusion for Urban Point-of-Interest Recommendation

Point-of-interest (POI) recommendation has a wide range of application values in smart city services computing. However, extreme sparsity of user-POI matrix seriously affects the recommendation accuracy. Rich contextual information is often utilized to solve data sparsity, whereas how to efficiently integrate them becomes another challenge. To this end, we merge the contextual information into probabilistic diffusion process to propose a novel approach, namely context-enhanced probabilistic diffusion, to generate satisfying POI recommendations under sparse data environment. First, the check-in data is preprocessed to construct the relevant scores that can reflect the relevant degrees between users and POIs expressly. Then, we extract social explicit and implicit trusts from user relationships, and integrate them with time influence to present a time-enhanced social diffusion process to obtain time-social probabilistic score. Next, by merging time factor into geographical distance, a time-enhanced geographical diffusion process is executed to generate time-geographical probabilistic score. Furthermore, we present a context-aware probabilistic matrix factorization to predict the relevant score for a target user on each POI. Finally, unchecked-in POIs with highest predicted relevant scores are recommended for the target user. Experiments executed on real-world datasets suggest that, the proposed approach outperforms the state-of-the-art approaches in terms of the recommendation accuracy.

EAGCN: An Efficient Adaptive Graph Convolutional Network for Item Recommendation in Social Internet of Things

In the era of Internet of Things (IoT), intelligent recommendation is playing an important role in our daily life. How to provide personalized information to users is the core concern of Internet content service providers. To improve the recommendation quality, it is a hot topic to go beyond merely user–item interaction records and take social relations into account in IoT. Recently, emerged graph neural networks (GNNs) shine a light on simulating the recursive social diffusion process, to refine user embedding learning. Nevertheless, two key issues have not been well studied in previous studies: 1) they usually model user preference and social influence within a same semantic space and fail to simultaneously inject high-order connectivity information reflected in both user–item interaction graph and user–user social graph and 2) they typically rely on negative sampling to optimize a recommendation model, which makes them highly sensitive to the design of the sampler and hardly makes full use of GPU’s computing ability. In light of this, we propose a novel framework for item recommendation, namely, an efficient adaptive graph convolutional network (EAGCN). Specifically, we introduce a space-adaptive graph convolutional module, which could jointly explore the propagation process of user interest and social influence. Furthermore, a user-specific gating mechanism is designed to aggregate user representations from both spaces. To make EAGCN practical in social IoT, we devise a fast nonsampling leaner to optimize EAGCN’s parameters with better leveraging matrix computing of GPU. Extensive experiments under four scenarios show that our solution consistently and significantly outperforms strong baseline methods in both model effectiveness and training efficiency.

DiffNet++: A Neural Influence and Interest Diffusion Network for Social Recommendation

Social recommendation has emerged to leverage social connections among users for predicting users’ unknown preferences, which could alleviate the data sparsity issue in collaborative filtering based recommendation. Early approaches relied on utilizing each user’s first-order social neighbors’ interests for better user modeling, and failed to model the social influence diffusion process from the global social network structure. Recently, we propose a preliminary work of a neural influence <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">Diff</i> usion <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">Net</i> work (i.e., DiffNet) for social recommendation L. Wu, P. Sun, Y. Fu, R. Hong, X. Wang, and M. Wang, “A neural influence diffusion model for social recommendation,” in <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">Proc. Int. ACM SIGIR Conf. Res. Develop. Inf. Retrieval</i> , 2019, pp. 235–244.. DiffNet models the recursive social diffusion process for each user, such that the influence diffusion hidden in the higher-order social network is captured in the user embedding process. Despite the superior performance of DiffNet, we argue that, as users play a central role in both user-user social network and user-item interest network, only modeling the influence diffusion process in the social network would neglect the latent collaborative interests of users hidden in the user-item interest network. To this end, in this paper, we propose DiffNet++, an improved algorithm of DiffNet that models the neural influence diffusion and interest diffusion in a unified framework. By reformulating the social recommendation as a heterogeneous graph with social network and interest network as input, DiffNet++ advances DiffNet by injecting both the higher-order user latent interest reflected in the user-item graph and higher-order user influence reflected in the user-user graph for user embedding learning. This is achieved by iteratively aggregating each user’s embedding from three aspects: the user’s previous embedding, the influence aggregation of social neighbors from the social network, and the interest aggregation of item neighbors from the user-item interest network. Furthermore, we design a multi-level attention network that learns how to attentively aggregate user embeddings from these three aspects. Finally, extensive experimental results on four real-world datasets clearly show the effectiveness of our proposed model. We release the source code at <uri xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">https://github.com/PeiJieSun/diffnet</uri> .

Social Interaction and Information Diffusion in Social Internet of Things: Dynamics, Cloud-Edge, Traceability

Social Internet of Things (SIoT), integrating the social networks and Internet of Things (IoT), leads to heterogeneous interactions of thing to thing, human to human, and human to thing, which in turn generates exploded information. Hence, as the soul of SIoT, information with its interaction and diffusion, records the track of humans and things and contains the hidden value for social administration and people's lives. Therefore, how to characterize the interplay between behavior spreading and information diffusion in SIoT is essential to predict and manage the information. Motivated by this, a more comprehensive understanding of the coupled modeling of social interaction and information diffusion processes in SIoT is conceived first. With the widespread adoption of cloud-edge computing, different nodes have different consciousness on information. Hence, a cloud-edge-aided information diffusion model is proposed for efficient interactions, which incorporates the role of edge in timely processing and feedback. On this basis, a blockchain-based cloud-edge SIoT architecture is proposed for traceability and security of information diffusion. Furthermore, the dynamical analysis of the coupled model in SIoT is provided, which illustrates the outbreak threshold, stability, and scale of information propagation. An interesting finding is that interactive behavior spreading only influences the final size of information propagation, not the spreading threshold. Extensive simulation results and detailed performance analysis verify the theoretical results, which are beneficial to provide traceable dissemination so as to find the most influential node and control the scale of information diffusion.

Seed Selection Strategies for Information Diffusion in Social Networks: An Agent-Based Model Applied to Rural Zambia

The successful adoption of innovations depends on the provision of adequate information to farmers. In rural areas of developing countries, farmers usually rely on their social networks as an information source. Hence, policy-makers and program-implementers can benefit from social diffusion processes to effectively disseminate information. This study aims to identify the set of farmers who initially obtain information (‘seeds’) that optimises diffusion through the network. It systematically evaluates different criteria for seed selection, number of seeds, and their interaction effects. An empirical Agent-Based Model adjusted to a case study in rural Zambia was applied to predict diffusion outcomes for varying seed sets ex ante. Simulations revealed that informing farmers with the most connections leads to highest diffusion speed and reach. Also targeting village heads and farmers with high betweenness centrality, who function as bridges connecting different parts of the network, enhances diffusion. An increased number of seeds improves reach, but the marginal effects of additional seeds decline. Interdependencies between seed set size and selection criteria highlight the importance of considering both seed selection criteria and seed set size for optimising seeding strategies to enhance information diffusion.

An offer you can't refuse: Enhancing personal productivity through ‘efficiency consumption’

Worldwide, economic growth is a prominent political goal, despite its severe conflicts with ecological sustainability. Contributing to the debate on economic ‘growth imperatives’, this article explores the thesis that both firms and consumers frequently acquire goods that increase their efficiency (productivity). For firms, efficiency is accepted as a main investment motive, but for consumers it is usually framed as convenience, ease, or comfort. Via social diffusion processes consumer goods that can save time and costs are transformed from a welcome expansion of possibilities into a social imperative whose noncompliance over time also has economic drawbacks. Positive feedback mechanisms not only lead to an acceleration of private life but favor ever more efficient industry and trade structures on the supply side, contributing to a redistribution of incomes and revenues. Eventually, a comprehensive consumption pattern leads to a new ‘normality’ and makes the renunciation of consumer goods like cars, computers or smartphones virtually impossible. Both microeconomics and consumption sociology generally assume fundamental differences in the motivations, goals and overall structural conditions of firms and consumers. Some reasons for this scholarly asymmetry are discussed and a more symmetrical consumption model is proposed.

Rekeying Cultural Scripts for Youth Suicide: How Social Networks Facilitate Suicide Diffusion and Suicide Clusters Following Exposure to Suicide

Research suggests that suicide can socially diffuse through social relationships and social contexts; however, little is known about the mechanisms that facilitate this diffusion. Using data from an in-depth case study of a cohesive community with an enduring youth suicide problem (N = 118), we examine how, after repeated exposure to suicide, the community’s cultural script for suicide may have been rekeyed such that suicide became a more imaginable option for some community youth. Essentially, we found evidence that a series of sudden, shocking, suicide deaths of high-status youth may have triggered the formation of new locally generalized meanings for suicide that became available, taken-for-granted social facts. The new meanings reinterpreted broadly shared adolescent experiences (exposure to pressure) as a cause of suicide facilitating youth’s ability to imagine suicide as something someone like them could do to escape. We conclude by discussing the implications of our findings for the scientific understanding of (1) suicide and suicide clusters, (2) social diffusion processes, and (3) suicide prevention.

Management innovation and social innovation: convergences and divergences

ObjetivoO objetivo deste artigo consiste em discutir os avanços mais recentes nos campos da inovação gerencial e da inovação social, na busca de possíveis aspectos convergentes e divergentes entre essas temáticas.Desenho/metodologia/abordagemAo examinar o estado da arte da literatura em ambas as temáticas, propõe-se um framework de abordagens teóricas, dimensões conceituais, metas e objetivos, processos, agentes, resultados, métodos e lacunas da literatura.ResultadosHá diferenças substanciais entre inovação gerencial e social em termos de fundamentos teóricos e conceituais. Embora ambas compartilhem semelhanças, dado o seu foco nas relações sociais e a relevância da tecnologia, seus processos de geração e difusão, entre outras características, são distintos.Limitações/implicações da pesquisaComo se trata de um artigo teórico sobre inovações que envolvem elementos sociais em sua essência, o desafio é incorporar a inovação tecnológica no framework teórico. Isso ajudaria pesquisas empiricamente orientadas sobre mais tipos de inovação.Implicações práticasA agenda de profissionais, acadêmicos, governo e sociedade civil deve levar em conta diferentes tipos de inovação, particularmente aquelas que vão além da tecnologia.Originalidade/valorEste artigo contribui para uma melhor compreensão das inovações que vão além da tecnologia, ao analisar inovações (no caso, as gerenciais e sociais) que possuem aspectos sociais como elementos centrais. Poucos pesquisadores analisaram conjuntamente esses tipos de inovações.

Contraception and the Fertility Transition

Three profound changes -- the mortality, fertility and contraception transitions -- characterized the Victorian era in England. Economists, following Becker (1960), focus on the first two and underplay the third by assuming couples can achieve their fertility target at no cost. The historical experience from Victorian England is at odds with this view of costless fertility regulation. We incorporate costly fertility limitation into the Becker paradigm: in our story, the mortality transition spurs on a contraception revolution which, in turn, makes it possible for the fertility transition to arrive. In the model, generationally-linked households with heterogeneous income choose between two contraception strategies, one traditional, the other modern. The modern comes with a higher fixed cost (reflecting social opposition and informational barriers characteristic of the times), but has a lower variable cost when it comes to averting childbirths. While the initial adopters of the modern technology are the rich -- those unfazed by the higher fixed cost -- eventually everyone switches so as to economize on the variable cost. What hastens theswitch is the decline in child mortality. Increased adoption of modern contraception unleashes a social diffusion process causing more people to switch, lowering fertility further and across all socioeconomic groups. The model is consistent with broad time-series and cross-sectional patterns ofthe English fertility transition.

Social diffusion of energy-related practices and representations: Patterns and policies in Portugal and Belgium

The social-class dimension of energy consumption has been rather neglected relative to other theoretical approaches to energy use, despite its potential deployment in energy policies. This paper aims at investigating energy policy-related inequalities across social classes with respect to three dimensions highlighted by environmental-justice theories: income distribution, procedures producing unequal distributional outcomes, and cultural and political recognition of vulnerable and marginalised social groups. These inequalities can be exacerbated or reduced by social diffusion processes, both vertical and horizontal. These processes include policy instruments intending to lower energy consumption in the residential sector. To empirically ground the analysis, two countries with contrasting patterns of income inequalities, Portugal and Belgium, are compared on the basis of qualitative data collected in 2009–2011. We discuss the relevance of integrating the social diffusion dimension in energy policies and propose several policy instruments to do so. One of our main contribution is to argue that both vertical and horizontal diffusion across social classes, if adequately translated into policy instruments, can boost the uptake of residential energy retrofits and other energy saving practices.

Computational Models of Social Influence and Collective Behavior

This chapter provides an overview of computational modeling of conformity, group deliberation, and social diffusion processes, with an emphasis on social psychological perspectives rather than the kinds of structural and institutional issues modeled in political science and sociology. The chapter attempts to illustrate the benefits of building maps of "parameter space" as a way to generalize across single studies and to develop out-of-sample new predictions.

SOCIAL DIFFUSION PROCESS MODELING IN LOCAL GOVERNMENT SYSTEM

The article represents the ways of social diffusion process modeling in local government system. Goal: to define possible parameters of the model using comparative analysis of some social diffusion models. Scientific novelty: Using regional research materials, for the first time ever we defined numeral values of communication frequency depending on the existing social structure among municipal unit residents and information reliability level. The received values of communication motivation frequency are necessary for practical use of the created model. Methodology: comparative analysis, correlation analysis. Results: We justified our chose of information as one of the possible objects of social diffusion, as it is the most significant part of effective municipal unit system performance. On the base of the author’s social research materials concerning municipal units in Zabaikalsky Krai (2011-2014), we defined variable values to create the model: communication motivation levels (communication frequency) depending on social structure of a community and information re-liability level concerning message content.

Early warning analysis for social diffusion events

There is considerable interest in developing predictive capabilities for social diffusion processes, for instance to permit early identification of emerging contentious situations, rapid detection of disease outbreaks, or accurate forecasting of the ultimate reach of potentially “viral” ideas or behaviors. This paper proposes a new approach to this predictive analytics problem, in which analysis of meso-scale network dynamics is leveraged to generate useful predictions for complex social phenomena. We begin by deriving a stochastic hybrid dynamical systems (S-HDS) model for diffusion processes taking place over social networks with realistic topologies; this modeling approach is inspired by recent work in biology demonstrating that S-HDS offer a useful mathematical formalism with which to represent complex, multi-scale biological network dynamics. We then perform formal stochastic reachability analysis with this S-HDS model and conclude that the outcomes of social diffusion processes may depend crucially upon the way the early dynamics of the process interacts with the underlying network’s community structure and core-periphery structure. This theoretical finding provides the foundations for developing a machine learning algorithm that enables accurate early warning analysis for social diffusion events. The utility of the warning algorithm, and the power of network-based predictive metrics, are demonstrated through an empirical investigation of the propagation of political “memes” over social media networks. Additionally, we illustrate the potential of the approach for security informatics applications through case studies involving early warning analysis of large-scale protests events and politically-motivated cyber attacks.

Assessing the Long-term Impacts of Water Quality Outreach and Education Efforts on Agricultural Landowners

We assess the long-term effectiveness of outreach and education efforts associated with a water quality improvement project in a watershed located in northern Utah, USA. Conducted 15 years after the original project began, our research examines the lasting impacts of different extension activities on landowners’ motivations to participate and their awareness and understanding of the water quality problem. Data were gathered by reviewing annual project reports, interviewing project staff about outreach and education efforts, and conducting in-depth, semi-structured interviews with a majority of the farmers and ranchers who participated in the project. The findings suggest that landowners were motivated to participate in the programme more by practical farm and household considerations and available cost-share opportunities than by particular environmental concerns. Previous relationships between farmers and government programme staff and one-on-one visits with landowners played an important role in their decisions to participate, while demonstration projects and peer-to-peer social diffusion processes played a much smaller role than expected. Although participants had a good grasp of the project goals, they did not have a strong sense of ownership of the water quality problem. These results suggest that education and outreach approaches centred only on the environmental dimensions of conservation projects may be insufficient to motivate changes in conservation behaviour. The results also suggest that conventional outreach strategies often did not have their presumed impact on landowners.

Diffusion in Congress: Social Dynamics of Discharge Petitions

While there is a vast literature highlighting the social dynamics that underlie political behavior, we know very little about the processes by which political behavior and practices disseminate among political actors. Drawing upon recent innovations, we study the diffusion of behavior within the U.S. House of Representatives. Specifically, we examine the role of diffusion in the context of discharge petitions, which are procedural mechanisms used to force a measure out of committee for floor consideration. Based on data from 1995 to 2008, we find that discharge petitions are subject to social diffusion processes. In fact, discharge petitions frequently follow a process of social learning according to which members rationally evaluate information conveyed by the decisions of other members. These findings have implications for our understanding of congressional processes in particular and questions of political accountability in general.

Associations between adolescent socioeducational status and use of snus and smoking

BackgroundFindings from studies on the association between smoking and socioeconomic status are mixed. While adolescent smoking is reduced in many countries, use of smokeless tobacco seems to increase. Associations between...

The Spatial Diffusion of Voting Participation: Qualitative and Quantitative Predictions as Solutions to the Laplace Equation

Political scientists have offered much evidence that political behavior and attitudes can spread or diffuse through society. For the most part, however, proof of diffusion is limited to excluding other alternatives and showing that a model is “consistent with” a social diffusion process. In legal terms, one might say that the evidence is circumstantial. This paper sets a higher goal for determining whether a diffusion process is behind a spatial distribution. Results will show that social diffusion of voting participation can lead to highly specific and predictable behavior patterns across a country, as seen in the United States and Russia, and that one can test for these patterns with qualitative and quantitative analyses.

The roles performed by peer educators during outreach among heroin addicts in India: Ethnographic insights

Peer-based outreach is a popular strategy in which former or current drug addicts are employed as peer educators to contact and educate out-of-treatment addicts. This study examines the interaction patterns that occur during outreach with particular regard to the roles that peer educators perform. Using ethnographic methods, it reports findings from a group of ‘peer educators’ and ‘clients’ from Yamuna Bazaar, New Delhi. In this context, peer educators assumed three roles that were co-constructed with clients: ‘counsellor’, ‘doctor’, and ‘role model’. Analysis of these role-plays revealed three significant patterns. First, the performances involved a hierarchical structuring with the peer educator in an authority position in nearly all interactions. Second, the role-plays were fluid and evolving with peer educators often transitioning across roles during the same interaction. Lastly, role performances appeared to have an underlying role replication mechanism in which roles were learned by first playing the subordinate role (e.g. ‘patient’) and then performing the dominant role (e.g. ‘doctor’) with another peer (e.g. new ‘patient’). These findings provide insight into issues of empowerment, peer relationship dynamics, and social diffusion processes among drug-using communities, and peer-based situations more generally.

Intermedia Processes in the Adoption of Tobacco Control Activities Among Opinion Leaders in California

This study uses the Diffusion of Innovations Theory to examine the role of mass media–generated interpersonal communication in the adoption of antitobacco norms among opinion leaders in California. Data were collected from 503 key community opinion leaders within 18 California counties in 1997 as part of the Independent Evaluation of the California Tobacco Control Program. Results provide support for the proposition that tobacco control policies and behaviors of opinion leaders can be categorized according to stages in the innovation decision process. As hypothesized, the level of mass media–generated interpersonal communication was dependent upon an individual’s stage of adoption such that the frequency of ad discussion increased with advancing stages on the continuum. Regression analyses also confirmed a strong positive associative trend between ad discussion and stage of adoption. Further analysis provided evidence that the impact of campaign exposure on adoption of antitobacco norms was mediated through discussion of the ads, highlighting the importance of social diffusion processes. This study provides evidence regarding the importance of using a stage-based framework to understand the role of communication channels at distinct stages of innovation adoption and among various community opinion leaders.

The Log-Logistic Rate Model

The log-logistic distribution is a widely used model in event history analysis. It is well-known that the log-logistic model is able to model social processes with monotonically decreasing, as well as nonmonotonic, reversed U-type hazard rates. In this article two three-parameter generalizations of the log-logistic model are introduced. These generalizations are very flexible in describing a great variety of processes with reversed U-type hazard rates. In addition, the first generalized model allows for separating upward rate shifts (intensity effects) from horizontal rate shifts (timing effects). With the second model it is possible to model immunity, that is, allow for the fact that some persons might not have an event at all. The usefulness of these models will be illustrated by an application to demographic data from the United States and Germany: The effects of education on marriage rates are analyzed. Finally, the relationship between the proposed hazard rate models and certain social diffusion processes is investigated.