Individual Retweeting Behavior on Social Networking Sites

Social networking sites(SNS) are conducive for information to go viral because numerous users are using SNS to receive and share information conveniently and efficiently. Therefore, SNS have become an important venue for businesses to diffuse information. However, there is a lack of a systematic and comprehensive research on individual retweeting behavior, which plays a fundamental role in information propagation on SNS. To bridge the research gaps and get an deeper understanding of individual retweeting behavior, this chapter proposes four research questions around this behavior, which are dealt with one by one in the following chapters. Specifially, Sect. 1.1 introduces the research background and raises research questions that fascinate us throughout the study. Sect. 1.2 elaborates both theoretical significance and practical significance of our research. Section 1.3 presents the detailed contents of our research and the structure of this monograph. The research methods adopted in this research are also briefly introduced. Finally, Sect. 1.4 summaries main innovation of our research and contributions.

Since individual retweeting behavior plays a pivotal role in information diffusion on social networking sites (SNS), investigating such behavior on SNS has become one of the hottest trends in SNS studies and drawn tremendous interest from multiple disciplines such as computer science, social communication, marketing, management and so on. Before delving into our study, it would be better to get a general picture of the related research in this field. Actually, existing studies on individual retweeting behavior can be divided into two classes, namely prediction-oriented research and explanation-oriented research. The former aims at accurately predicting new observations by establishing predictive models (statistical models and other methods such as data mining algorithms), while the latter focuses on explanation and is grounded on underlying causal relationships between theoretical constructs. At the very beginning of this chapter, key concetps in this monograph will be explained in detail. And then, we will spend two sections to introduce prior research in the above two classes. After that, the theoretical foundation of this monograph will be introduced. Finally, we will make some comment on existing research and conclude this chapter.

From the literature review in Chap. 2, we can see that prior studies on determinants of individual information dissemination decisions is fragmented, and little has been done to integrate existing findings. To tackle this problem, we develop an overarching theoretical framework to investigate the decision-making process of individual retweeting behavior based on the Elaboration-Likelihood Model (ELM) and existing studies. Influential factors on the peripheral route and the central route are identified and examined based on information processing theory, bandwagon effect and prior studies. Hypotheses related to the direct effect, mediating effect and moderating effect are introduced in detail. Finally, we elaborate on the dataset used in this monograph, varable measurements and statistical models employed to validate those hypotheses in the conceptual model.

In Chap. 3, we identify some influential factors that have an positive impact on individual retweeting behavior, such as topical relevance, information richness, soical tie strength, etc. One may wonder whether these factors only play an important role in theroy or, are these factors still important when predicting individual retweeting behavior? Furthermoer, to the best of our knowledge, virtually no scholarly effort has been undertaken to figure out the relative importance of those factors when predicting individual retweeting decision. Instead, a large number of features are indiscriminately introduced into the prediction model without examining the relevance of these features. The existence of redundant features not only increases data collection cost, but also tends to generate an overfitted model which predicts poorly on future observations not used in model training, known as the curse of dimensionality. Thus, it is necessary to rank the priority of these factors and find out the dominating ones. To tackle the above problems, we first pick out a specific user to illustrate the feature (also called factor in the monograph) selection process. The results confirm that only a small subset of predictors have an influential impact on individual retweeting behavior. And then, based on a large sample, we commit ourselves to find out factors that are not only important in theory in terms of explaining individual retweeting behavior, but also important in practice in terms of predicting individual retweeting behavior. Finally, we obtain a subset of dominating factors which not only save the cost of collecting trivial features but also improve the prediction performance to some extent, under certain classification algorithms such as support vector classification (SVC) or logistic.

In order to systematically explain individual information dissemination behavior on SNS, Chap. 3 proposes an overarching theoretical model to examine an individual’s retweeting decision making process, which is illustrated in Fig. 3.​1. This conceptual model mainly consists of two parts: determinants of individual retweeting behavior (\(H1 \sim H8\)) and moderators of individual retweeting behavior (\(H9 \sim H11\)). This chapter focuses on validating the first part presented in Fig. 5.1 and next chapter will examine the moderating factors. Regression results in this chapter show that both the central route and the peripheral route have significant impacts on individual retweeting decisions. Among them, topical relevance, social tie strength and value homophily are the most important ones, followed by information richness(#URL, #hashtag), #mention and informational social influence. Author-related factors such as source trustworthiness have trivial impacts. Existing studies about the impacts of the relationships between the source and the receiver on the receiver’s information retweeting behavior are still controversial. In this chapter, we propose and validate that social tie strength partially mediates the effect of value homophily on individual retweeting behavior, which offers at least one explanation for the contradictory findings about the effect of homophily on individual sharing behavior in previous research.

Nowadays, companies are increasingly utilizing customized advertising on social networking sites. By connecting advertisements with customers’ favorite idols, music, topics etc., companies hope individuals will dwell on the information and share it with others. We claim that individuals should be given different considerations as different groups have distinct retweeting responses to customized advertising. In this chapter, we examine factors which moderate the relationship between topical relevance of online content and individual retweeting behavior, including characteristics of tweets and individuals, and interpersonal relationships. This research is the first to employ the Elaboration-Likelihood Model to study three types of moderators in individual retweeting behavior on SNS. The results reveal that an in-depth investigation of the relationship between topical relevance of a message and individual retweeting behavior is necessary and important. We also confirm that the hierarchical linear model has several advantages over previous models employed to study individual retweeting behavior on SNS.

As the last chapter, summaries the research findings of this monograph from three aspects and elaborates the contributions both in practice and in theory. And then limitations and directions for future research are highlighted.