Quantification of Sensible Temperature by Analyzing Meteorological Information and Tweet Data and Its Application to Demand Forecasting

Takashi MAGA  Kenta MIKAWA  Masayuki GOTO  Tomohiro YOSHIKAI  

D - Abstracts of IEICE TRANSACTIONS on Information and Systems (Japanese Edition)   Vol.J101-D   No.7   pp.1037-1051
Publication Date: 2018/07/01
Online ISSN: 1881-0225
Type of Manuscript: PAPER
meteorological information,  SNS,  Twitter,  sensible temperature,  demand forecasting,  

Full Text(in Japanese): PDF(1.8MB)
>>Buy this Article

It is important to quantify the sensible temperature which consumers feel more than absolute meteorological data. The previous studies have been revealed that sensible temperature is mainly affected by weather conditions such as relative humidity and wind-speed. However, the sensible temperature is affected by not only weather conditions but also human conditions such as amount of wearing clothes and metabolic rate, and there are various quantifying ways. In this study, we propose the method of quantifying the sensible temperature by utilizing the large-scale tweet data and consider the effectiveness of the obtained sensible temperature for demand forecasting.