Human mobility forecasting with region-based flows and geotagged Twitter data

作者：

Highlights：

• A novel approach for nation-wide human mobility forecasting is proposed.

• The predictor combines mobile-phone and Twitter location data as input variables.

• LSTM and VAR models have been tested as candidates to develop the mechanism.

• Twitter has proved to be a suitable exogenous input.

• The system has been tested in Spain achieving a 6.85 CRMSE for 7-day prediction.

摘要

•A novel approach for nation-wide human mobility forecasting is proposed.•The predictor combines mobile-phone and Twitter location data as input variables.•LSTM and VAR models have been tested as candidates to develop the mechanism.•Twitter has proved to be a suitable exogenous input.•The system has been tested in Spain achieving a 6.85 CRMSE for 7-day prediction.

论文关键词：Human mobility,Machine learning,Prediction model,Online social network,Twitter

论文评审过程：Received 7 July 2021, Revised 14 December 2021, Accepted 28 April 2022, Available online 10 May 2022, Version of Record 14 May 2022.

论文官网地址：https://doi.org/10.1016/j.eswa.2022.117477