A Forecast Model of Tourism Demand Driven by Social Network Data

Tao Peng,Chenjie Wang,Jian Chen,Yanshi Cao

doi:10.1109/access.2021.3102616

Abstract

To improve the forecasting accuracy of tourism demand through forecasting model and data sources, this paper takes the social network data as an entry point, and collects the social network data by the web crawler, then quantifies the data based on the sentiment analysis of the BERT model. This paper uses structured variables such as social network data, weather, holidays, etc. to build a tourism demand forecasting model based on Gradient Boosting Regression Trees. At last, take Huang Shan as example, use actual statistics of passenger terminal and social network data to do an empirical analysis of Huang Shan tourism demand forecasting. Compared with the existing model and introduce ablation study to verify the effectiveness of the considered factors. The result shows that the model based on social network data has improved the forecasting accuracy from the existing ones, ablation study shows social network data helps to improve the accuracy of tourism demand forecasting.

Highlights

With the continuous development of the social economy, the demand for tourist passenger transportation is increasing
Compared with the competition model, the error of our model is reduced by 9.74%
GBRT is one of ensemble learning model, MAPE of GBRT model excluding social network data is 11.27%, and the MAPE of support vector regression (SVR) model is 14.48%, this shows that GBRT model still has better prediction effect when using the same variables as the comparison model

Summary

INTRODUCTION

With the continuous development of the social economy, the demand for tourist passenger transportation is increasing. Models for tourist arrivals focus on long-term prediction (e.g monthly, quarterly, and annual) of relatively large areas (e.g provinces, countries, and regions) These models provide references for formulating macro tourism policies, but for specific tourist attractions, short-term forecasts (e.g daily) is more important. It is urgent to use social network data to accurately predict passenger demand in tourist attractions. The paper uses the Gradient Boosting Regression Trees(GBRT) to forecast the tourism demand, and develops the application of model in the field of tourism demand prediction. A Gradient Boosting Regression Trees prediction model based on social network data is used to improve the prediction accuracy of tourism demand and make up for the deficiencies of existing research in terms of models and data. The method proposed in this paper mainly aimd at the prediction of tourism demand under normal circumstances, and may not use the prediction of tourism demand under major public health events

DATA COLLECTION

TOURISM DEMAND FORECASTING MODEL

Findings

CONCLUSION