Comparing content marketing strategies of digital brands using machine learning

Abstract

AbstractThis study identifies and recommends key cues in brand community and public behavioral data. It proposes a research framework to strengthen social monitoring and data analysis, as well as to review digital commercial brands and competition through continuous data capture and analysis. The proposed model integrates multiple technologies, analyzes unstructured data through ensemble learning, and combines social media and text exploration technologies to examine key cues in public behaviors and brand communities. The results reveal three main characteristics of the six major digital brands: notification and diversion module; interaction and diversion module; and notification, interaction, and diversion module. This study analyzes data to explore consumer focus on social media. Prompt insights on public behavior equip companies to respond quickly and improve their competitive advantage. In addition, the use of community content exploration technology combined with artificial intelligence data analysis helps grasp consumers’ information demands and discover unstructured elements hidden in the information using available Facebook resources.