Development of Viral Marketing Techniques in Online Social Networks for E-commerce automated by Data Analytics Software

Description

With the emergence of a plethora of online social networks and their huge number of users, innovative digital applications in online social networks that leverage the interaction and influence of online social network users have become increasingly important to mobile e-commerce. The wide availability of digital data in online social networks and the enormous user pool offers an interesting question on estimating the influence of users based on the user interaction over time. This online interaction over the online social network gives rise to a real-time interaction network that represents a fundamental medium for spreading and captures important characteristics on how information can diffuse. A prominent example is Facebook in which the digital contents (e.g., user status updates, posts, photos, videos, links) of a Facebook user are viewable on a Facebook Timeline by others who can interact with them (such as clicking the Facebook Like endorsement button for a post). These online interactions are recorded on the Facebook Timeline that again lead to more interaction. Here, the spreading process increases the susceptibility of other users to the same; this results in the successive spread of a digital message from a few users to many more. From viral marketing and other e-commerce applications viewpoint, it is interesting to study the spreading impetus of a digital word-of-mouth engine starting from a selected few. Due to the complex inter-coupling of online social networks and their software interdependency with other cyber-networks, it can be a challenge to find the most effective marketer or to design e-commerce protocols that can identify reliable spreader that can maximize the reach of influence in the shortest amount of time. There are several key challenges in the development of this digital viral marketing application: PH. o8w to design the right number of observations or adaptive measurements such that the influential spreaders can be correctly detected? How to monitor this spreading dynamics that are constrained by the complex multi-layered online social network topology representing direct connectivity and interaction over time? We will develop the theories and algorithms to answer these questions and develop the software implementation in major online social networks such as Facebook, Twitter and Weibo for companies who maintain an online social network presence to deploy viral marketing e-commerce.