BackgroundOnline health communities (OHCs) have become a major source of social support for people with health problems. Members of OHCs interact online with similar peers to seek, receive, and provide different types of social support, such as informational support, emotional support, and companionship. As active participations in an OHC are beneficial to both the OHC and its users, it is important to understand factors related to users’ participations and predict user churn for user retention efforts.ObjectiveThis study aimed to analyze OHC users’ Web-based interactions, reveal which types of social support activities are related to users’ participation, and predict whether and when a user will churn from the OHC.MethodsWe collected a large-scale dataset from a popular OHC for cancer survivors. We used text mining techniques to decide what kinds of social support each post contained. We illustrated how we built text classifiers for 5 different social support categories: seeking informational support (SIS), providing informational support (PIS), seeking emotional support (SES), providing emotional support (PES), and companionship (COM). We conducted survival analysis to identify types of social support related to users’ continued participation. Using supervised machine learning methods, we developed a predictive model for user churn.ResultsUsers’ behaviors to PIS, SES, and COM had hazard ratios significantly lower than 1 (0.948, 0.972, and 0.919, respectively) and were indicative of continued participations in the OHC. The churn prediction model based on social support activities offers accurate predictions on whether and when a user will leave the OHC.ConclusionsDetecting different types of social support activities via text mining contributes to better understanding and prediction of users’ participations in an OHC. The outcome of this study can help the management and design of a sustainable OHC via more proactive and effective user retention strategies.

Abstract-In this paper, we study the resilience of supply networks against disruptions and provide insights to supply chain managers on how to construct a resilient supply network from the perspective of complex network topologies. Our goal is to study how different network topologies, which are created from different growth models, affect the network's resilience against both random and targeted disruptions. Of particular interest are situations where the type of disruption is unknown. Using a military logistic network as a case study, we propose new network resilience metrics that reflect the heterogeneous roles (e.g., supply, relay, and demand) of nodes in supply networks. We also present a hybrid and tunable network growth model called Degree and Locality-based Attachment (DLA), in which new nodes make connections based on both degree and locality. Using computer simulations, we compare the resilience of several supply network topologies that are generated with different growth models. The results show that the new resilience metrics can capture important resilience requirements for supply networks very well. We also found that the supply network topology generated by the DLA model provides balanced resilience against both random and targeted disruptions.

Through the development and usage of an agent‐based model, this article investigates firms' adaptive strategies against disruptions in a supply chain network. Viewing supply chain networks as complex adaptive systems, we first construct and analyze a real‐world supply chain network among 2,971 firms spanning 90 industry sectors. We then develop an agent‐based simulation to show how the model of firms' adaptive behaviors can leverage competition relationships within a supply chain network. The simulation also models how disruptions propagate in the supply chain network through cascading failures. With the simulation, we seek to understand if a firm's adaptive behaviors can reduce the impact of disruptions in supply chain networks. Therefore, we propose, evaluate, and analyze two types of adaptive strategies a firm can leverage to reduce the negative effects of supply chain network disruptions. First, we deploy in our model a reactive strategy, which restructures the network in response to a disruption event among first‐tier suppliers. Next, we develop and propose proactive strategies, which are used when a distant disruption is observed but has not yet hit the focal firm. We discuss the implications related to how and when firms can improve their resilience against supply disruptions by leveraging adaptive strategies.

Online cancer communities help members support one another, provide new perspectives about living with cancer, normalize experiences, and reduce isolation. The American Cancer Society's 166000-member Cancer Survivors Network (CSN) is the largest online peer support community for cancer patients, survivors, and caregivers. Sentiment analysis and topic modeling were applied to CSN breast and colorectal cancer discussion posts from 2005 to 2010 to examine how sentiment change of thread initiators, a measure of social support, varies by discussion topic. The support provided in CSN is highest for medical, lifestyle, and treatment issues. Threads related to 1) treatments and side effects, surgery, mastectomy and reconstruction, and decision making for breast cancer, 2) lung scans, and 3) treatment drugs in colon cancer initiate with high negative sentiment and produce high average sentiment change. Using text mining tools to assess sentiment, sentiment change, and thread topics provides new insights that community managers can use to facilitate member interactions and enhance support outcomes.

This paper proposes a decision support system to aid movie investment decisions at the early stage of movie productions. The system predicts the success of a movie based on its profitability by leveraging historical data from various sources. Using social network analysis and text mining techniques, the system automatically extracts several groups of features, including "who" are on the cast, "what" a movie is about, "when" a movie will be released, as well as "hybrid" features that match "who" with "what", and "when" with "what". Experiment results with movies during an 11-year period showed that the system outperforms benchmark methods by a large margin in predicting movie profitability. Novel features we proposed also made great contributions to the prediction. In addition to designing a decision support system with practical utilities, our analysis of key factors for movie profitability may also have implications for theoretical research on team performance and the success of creative work.

No abstract

We propose that the emergent phenomenon know as ''desakota,'' the rapid urbanization of densely populated rural populations in the newly developed world, particularly China, can be simulated using agent-based models that combine bottom-up actions with global interactions. We argue that desakota represents a surprising and unusual form of urbanization well-matched to processes of land development that are locally determined but moderated by the higher-level macroeconomy. We develop a simple logic that links local household reform to global urban reform, translating these ideas into a model structure that reflects these two scales. Our model first determines the rate of growth of different spatial aggregates using linear statistical analysis. It then allocates this growth to the local level using ''developer agents'' who determine the transformation or mutation of rural households to urban pursuits based on local land costs, accessibilities, and growth management practices. The model is applied to desakota development in the Suzhou region for the period 1990 to 2000. We show how the global rates of change predicted at the township level in the Wuxian City region surrounding Suzhou are tempered by local transformations of rural to urban land uses which we predict using cellular automata rules. The model is implemented in the RePast 3 software and is validated using a blend of data taken from remote sensing and government statistical sources. It represents an example of generative social science that fuses plausible behavior with formalized logics matched against empirical evidence, essential in showing how novel patterns of urbanization such as desakota emerge.

No abstract