Loading...
Paper Number
2614
Paper Type
short
Description
As social media platforms facilitate user interactions, organizations increasingly use social media networks (SMNs) to build network ties. Studying user behavior on SMNs can help to uncover strategic information and improve situation awareness. However, there is a lack of understanding of behavioral drivers of SMN participants. This research developed a theoretically-based IS development framework for modeling user behavior in large evolving SMNs. To demonstrate the feasibility of our framework, we developed a proof-of-concept system for simulating user activities in the SMNs of Twitter social communities. Our system models the complex behavioral features in the SMNs by using a wide range of theoretically-driven features and machine-discovered features, and predicts user activities by using a pipeline of statistical and machine-learning techniques. Preliminary results of a simulation study provide insights of the importance of comprehensive network features to model SMN group behavior accurately and quality of commitment features to model SMN user behavior.
Recommended Citation
Chung, Wingyan, "Understanding Behavioral Drivers in Twitter Social Media Networks" (2023). ICIS 2023 Proceedings. 9.
https://aisel.aisnet.org/icis2023/socmedia_digcollab/socmedia_digcollab/9
Understanding Behavioral Drivers in Twitter Social Media Networks
As social media platforms facilitate user interactions, organizations increasingly use social media networks (SMNs) to build network ties. Studying user behavior on SMNs can help to uncover strategic information and improve situation awareness. However, there is a lack of understanding of behavioral drivers of SMN participants. This research developed a theoretically-based IS development framework for modeling user behavior in large evolving SMNs. To demonstrate the feasibility of our framework, we developed a proof-of-concept system for simulating user activities in the SMNs of Twitter social communities. Our system models the complex behavioral features in the SMNs by using a wide range of theoretically-driven features and machine-discovered features, and predicts user activities by using a pipeline of statistical and machine-learning techniques. Preliminary results of a simulation study provide insights of the importance of comprehensive network features to model SMN group behavior accurately and quality of commitment features to model SMN user behavior.
When commenting on articles, please be friendly, welcoming, respectful and abide by the AIS eLibrary Discussion Thread Code of Conduct posted here.
Comments
15-SocialMedia