Forecasting and Analyzing Brand Communication Trends in the Exhibition Industry Driven by Big Data

Abstract

This study aims to predict and analyze brand communication trends in the exhibition industry, leveraging the power of big data analytics. Given the growing significance of data-driven strategies in enhancing brand engagement, our research is particularly relevant for stakeholders in the exhibition sector. The complexity arises from the vast and heterogeneous nature of data sources, including social media platforms, exhibition websites, and customer feedback databases. To address this challenge, we employed a systematic approach encompassing data collection, preprocessing, feature selection, and model development using various machine learning algorithms. Data was meticulously extracted, cleaned, and transformed for analysis. Feature importance was determined through TF-IDF and Random Forest techniques, with Social Media Engagement emerging as a critical factor. We developed predictive models, including Linear Regression, Support Vector Machine (SVM), and Neural Network, and evaluated their performance using metrics such as Mean Absolute Error (MAE), Root Mean Squared Error (RMSE), and R-squared (). The Neural Network model exhibited superior performance, highlighting its high predictive accuracy. Trend analysis revealed a significant increase in social media usage, a positive correlation with customer feedback, and a substantial impact of exhibition attendance on brand communication. These findings underscore the transformative potential of big data analytics in refining brand communication strategies within the exhibition industry.