Examining logistics developments in post-pandemic Japan through sentiment analysis of Twitter data
Enna Hirata, Takuma Matsuda
Abstract
The objective of this study is to utilize natural language processing technologies to examine data gathered from Twitter related to logistics in Japan during the COVID-19 pandemic. The Bidirectional Encoder Representations from Transformers (BERT) machine learning model is utilized to assess the sentiment of the content. The findings suggest a positive outlook on logistics during time frame analyzed. This research has four key implications: (1) the sentiment towards the term "logistics" is generally positive as per our analysis; (2) there is a trend of increasing interest in logistics in western Japan in 2022; (3) social media can be utilized as a tool to address the challenges faced by the logistics industry; and (4) our research highlights the potential of using social media data to provide a more timely and comprehensive analysis of logistics and transportation trends.