This book explores and analyzes influential predictors and the underlying mechanisms of individual content sharing/retweeting behavior on social networking sites (SNS) from an empirical perspective. Since Individual content sharing/ retweeting behavior expedites information dissemination, it is a critical mechanism of information diffusion on Twitter.
Individual sharing/retweeting behavior does not appear to happen randomly. So, what factors lead to individual information dissemination behavior? What are the dominating predictors? How does the recipient make retweeting decisions? How do these influential predictors combine and by what mechanism do they influence an individual’s retweeting decisions? Furthermore, are there any differences in the process of individual retweeting decisions? If so, what causes such differences?
In order to answer these previously unexplored questions and gain a holistic view of individual retweeting behavior, the authors examined people’s retweeting history on Twitter and obtained a real dataset containing more than 60 million Twitter posts. They then employed text mining and natural language processing techniques to extract useful information from social media content, and used various feature selection methods to identify a subset of salient features that have substantial effects on individual retweeting behavior. Lastly, they applied the Elaboration Likelihood Model to build an overarching theoretical framework to reveal the underlying mechanisms of individual retweeting behavior. Given its scope, this book will appeal to researchers interested in investigating information dissemination on social media, as well as to marketers and administrators who plan to use social networking sites as an important avenue for information dissemination.
Author(s): Juan Shi, Kin Keung Lai, Gang Chen
Publisher: Springer Singapore
Year: 2020
Language: English
Pages: 152
City: Singapore
Preface
Acknowledgements
Contents
Acronyms
1 Introduction
1.1 Research Background and Research Questions
1.1.1 Research Background
1.1.2 Research Questions
1.2 Research Significance
1.2.1 Theoretical Significance
1.2.2 Practical Significance
1.3 Research Content and Technical Route
1.3.1 Research Content
1.3.2 Structure of the Monograph
1.3.3 Technical Route
1.4 Main Innovation and Contributions
References
2 Literature Review and Theoretical Foundation
2.1 Introduction
2.2 Definition of Concepts
2.2.1 Social Networking Sites
2.2.2 Twitter
2.2.3 Tweet
2.2.4 User's Behavior on SNS
2.3 Explanation-Oriented Studies on Individual Retweeting Behavior
2.3.1 Research Emphasizing the Information Carrier
2.3.2 Research Emphasizing both the Information Source and the Information Carrier
2.3.3 Research Emphasizing Individual Preferences
2.3.4 Research Emphasizing Relationships
2.4 Prediction-Oriented Studies on Individual Retweeting Behavior
2.5 Theoretical Foundation
2.5.1 The Elaboration-Likelihood Model
2.5.2 Why Using ELM in the Current Research
2.6 Commentary on Related Literature
References
3 Research Scheme Design
3.1 Introduction
3.2 A Conceptual Framework of Individual Retweeting Behavior on SNS
3.2.1 Analyzing Factors on the Central Route
3.2.2 Analyzing Factors on the Peripheral Route
3.2.3 The Mediating Role of Social Tie Strength
3.2.4 Analyzing Moderators on the Central Route
3.3 Method
3.3.1 Data Collection
3.3.2 Measure
3.3.3 Data Analysis Methods
3.4 Conclusion
References
4 Dominating Factors Affecting Individual Retweeting Behavior
4.1 Introduction
4.2 Verification of the Non-randomness of Individual Retweeting Behavior
4.2.1 Verification from Social Interaction Perspective
4.2.2 Verification from Topical Perspective
4.3 Ranking Factors Affecting Individual Retweeting Behavior—An Example
4.3.1 A Highly Discriminating Feature: Topic_distance
4.3.2 Ranking Factors on a Specific User
4.4 Ranking Factors on a Large Sample
4.4.1 Feature Selection Using Filter Models on a Large Sample
4.4.2 Feature Selection Using Hybrid Model on a Large Sample
4.4.3 Feature Selection Using Other Method on a Large Sample
4.4.4 Analysis of Feature Selection Results
4.5 Prediction Performance of Salient Factors
4.6 Conclusion and Discussion
References
5 Direct Effect and Mediating Effect of Individual Retweeting Behavior on SNS
5.1 Introduction
5.2 Data Pre-processing and Descriptive Analysis
5.3 Methodology
5.4 Results
5.4.1 Hypotheses Test of Factors on the Central Route
5.4.2 Hypotheses Test of Factors on the Peripheral Route
5.4.3 Hypotheses Test of the Mediating Effect
5.4.4 Ranking of Factors
5.5 Understanding Users with Different Retweeting Behavior
5.6 Conclusion and Discussion
References
6 Moderating Effect of Individual Retweeting Behavior on SNS
6.1 Introduction
6.2 Data Pre-processing and Descriptive Analysis
6.3 Methodology
6.4 Results
6.4.1 Hypotheses Test of Moderating Factors—Individual Characteristics
6.4.2 Hypotheses Test of Moderating Factors—Interpersonal Relationships
6.4.3 Hypotheses Test of Moderating Factors—Tweet Characteristics
6.4.4 Model Diagnostics: Individual Heterogeneity
6.4.5 Robustness Test
6.5 Conclusion and Discussion
References
7 Conclusion and Discussion
7.1 Summary of Findings
7.2 Contribution and Implications
7.2.1 Implications for Research
7.2.2 Managerial Contribution
7.3 Limitations
7.4 Directions for Future Research
References
