Social Media Data-Driven Research on Interdisciplinary Theories of Economics

Abstract

With the rapid development of social media, the data generated by social platforms provides unprecedented perspectives and opportunities for economic research. As a big data source, social media provides rich basic data support for economic theory innovation due to its unique dynamic, unstructured characteristics and large-scale user participation. The core goal of this paper is to promote the innovation of economic theoretical frameworks by introducing machine learning techniques and interdisciplinary research methods. Firstly, through the acquisition and analysis of large-scale social media data, this study reveals the relationship between user behavior patterns and economic dynamics. Secondly, natural language processing, deep learning and graph neural networks are used to explore new applications in market forecasting, consumer behavior modeling and group decision analysis. This paper also focuses on how social media data can provide intelligent support for policy formulation and business practice, and promote policy optimization and business model innovation. Through this research, this paper aims to provide a new perspective for economic research, promote the progress of theories and the effective implementation of policies, and facilitate data-driven decision-making in business practice.