Would you please like my tweet?! An artificially intelligent, generative probabilistic, and econometric based system design for popularity-driven tweet content generation

Abstract

An understudied area in the field of social media research is the design of decision support systems that can aid the manager by way of automated message component generation. Recent advances in this form of artificial intelligence has been suggested to allow content creators and managers to transcend their tasks from creation towards editing, thus overcoming a common problem: the tyranny of the blank screen. In this research, we address this topic by proposing a novel system design that will suggest engagement-driven message features as well as automatically generate critical and fully written unique Tweet message components for the goal of maximizing the probability of relatively high engagement levels. Our multi-methods design relies on the use of econometrics, machine learning, and Bayesian statistics, all of which are widely used in the emerging fields of Business and Marketing Analytics. Our system design is intended to analyze Tweet messages for the purpose of generating the most critical components and structure of Tweets. We propose econometric models to judge the quality of written Tweets by way of engagement-level prediction, as well as a generative probability model for the auto-generation of Tweet messages. Testing of our design demonstrates the need to take into account the contextual, semantic, and syntactic features of messages, while controlling for individual user characteristics, so that generated Tweet components and structure maximizes the potential engagement levels.