In a social network, adoption probability refers to the probability that a social entity will adopt a product, service, or opinion in the foreseeable future. Such probabilities are central to fundamental issues in social network analysis, including the influence maximization problem. In practice, adoption probabilities have significant implications for applications ranging from social network-based target marketing to political campaigns, yet predicting adoption probabilities has not received sufficient research attention. Building on relevant social network theories, we identify and operationalize key factors that affect adoption decisions: social influence, structural equivalence, entity similarity, and confounding factors. We then develop the locally weighted expectation-maximization method for Naïve Bayesian learning to predict adoption probabilities on the basis of these factors. The principal challenge addressed in this study is how to predict adoption probabilities in the presence of confounding factors that are generally unobserved. Using data from two large-scale social networks, we demonstrate the effectiveness of the proposed method. The empirical results also suggest that cascade methods primarily using social influence to predict adoption probabilities offer limited predictive power and that confounding factors are critical to adoption probability predictions.
Increasing global connectivity makes emerging infectious diseases (EID) more threatening than ever before. Various information systems (IS) projects have been undertaken to enhance public health capacity for detecting EID in a timely manner and disseminating important public health information to concerned parties. While those initiatives seemed to offer promising solutions, public health researchers and practitioners raised concerns about their overall effectiveness. In this paper, we argue that the concerns about current public health IS projects are partially rooted in the lack of a comprehensive framework that captures the complexity of EID management to inform and evaluate the development of public health IS. We leverage loose coupling to analyze news coverage and contact tracing data from 479 patients associated with the severe acute respiratory syndrome (SARS) outbreak in Taiwan. From this analysis, we develop a framework for outbreak management. Our proposed framework identifies two types of causal circles—coupling and decoupling circles—between the central public health administration and the local capacity for detecting unusual patient cases. These two circles are triggered by important information-centric activities in public health practices and can have significant influence on the effectiveness of EID management. We derive seven design guidelines from the framework and our analysis of the SARS outbreak in Taiwan to inform the development of public health IS. We leverage the guidelines to evaluate current public health initiatives. By doing so, we identify limitations of existing public health IS, highlight the direction future development should consider, and discuss implications for research and public health policy.