Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Recent Surge in Public Interest in Transportation: Sentiment Analysis of Baidu Apollo Go Using Weibo Data

Shiqi Wang, Zhouye Zhao, Yuhang Xie, Mingchuan Ma, Zirui Chen, Zeyu Wang, Bohao Su, Wenrui Xu, Tianyi Li

TL;DR

This study analyzes public sentiment toward Baidu Apollo Go, a leading autonomous ride-hailing service in China, using 36,096 Weibo posts from January to July 2024. A fine-tuned Chinese BERT classifier is trained on 2,697 manually labeled posts to identify Positive, Neutral, and Negative attitudes, enabling temporal and spatial analysis across 11 operational regions. Results reveal a July surge in online discussion (87+% of posts) with sentiment shifting from predominantly positive to rising negative commentary as the topic gains intensity, and regional patterns showing coastal and operational provinces driving discourse. The work provides actionable insights for planners and policymakers, including the role of media coverage and the socioeconomic concerns around automation, and delivers reproducible resources via Hugging Face and GitHub repositories.

Abstract

Urban mobility and transportation systems have been profoundly transformed by the advancement of autonomous vehicle technologies. Baidu Apollo Go, a pioneer robotaxi service from the Chinese tech giant Baidu, has recently been widely deployed in major cities like Beijing and Wuhan, sparking increased conversation and offering a glimpse into the future of urban mobility. This study investigates public attitudes towards Apollo Go across China using Sentiment Analysis with a hybrid BERT model on 36,096 Weibo posts from January to July 2024. The analysis shows that 89.56\% of posts related to Apollo Go are clustered in July. From January to July, public sentiment was mostly positive, but negative comments began to rise after it became a hot topic on July 21. Spatial analysis indicates a strong correlation between provinces with high discussion intensity and those where Apollo Go operates. Initially, Hubei and Guangdong dominated online posting volume, but by July, Guangdong, Beijing, and international regions had overtaken Hubei. Attitudes varied significantly among provinces, with Xinjiang and Qinghai showing optimism and Tibet and Gansu expressing concerns about the impact on traditional taxi services. Sentiment analysis revealed that positive comments focused on technology applications and personal experiences, while negative comments centered on job displacement and safety concerns. In summary, this study highlights the divergence in public perceptions of autonomous ride-hailing services, providing valuable insights for planners, policymakers, and service providers. The model is published on Hugging Face at https://huggingface.co/wsqstar/bert-finetuned-weibo-luobokuaipao and the repository on GitHub at https://github.com/GIStudio/trb2024.

Recent Surge in Public Interest in Transportation: Sentiment Analysis of Baidu Apollo Go Using Weibo Data

TL;DR

This study analyzes public sentiment toward Baidu Apollo Go, a leading autonomous ride-hailing service in China, using 36,096 Weibo posts from January to July 2024. A fine-tuned Chinese BERT classifier is trained on 2,697 manually labeled posts to identify Positive, Neutral, and Negative attitudes, enabling temporal and spatial analysis across 11 operational regions. Results reveal a July surge in online discussion (87+% of posts) with sentiment shifting from predominantly positive to rising negative commentary as the topic gains intensity, and regional patterns showing coastal and operational provinces driving discourse. The work provides actionable insights for planners and policymakers, including the role of media coverage and the socioeconomic concerns around automation, and delivers reproducible resources via Hugging Face and GitHub repositories.

Abstract

Urban mobility and transportation systems have been profoundly transformed by the advancement of autonomous vehicle technologies. Baidu Apollo Go, a pioneer robotaxi service from the Chinese tech giant Baidu, has recently been widely deployed in major cities like Beijing and Wuhan, sparking increased conversation and offering a glimpse into the future of urban mobility. This study investigates public attitudes towards Apollo Go across China using Sentiment Analysis with a hybrid BERT model on 36,096 Weibo posts from January to July 2024. The analysis shows that 89.56\% of posts related to Apollo Go are clustered in July. From January to July, public sentiment was mostly positive, but negative comments began to rise after it became a hot topic on July 21. Spatial analysis indicates a strong correlation between provinces with high discussion intensity and those where Apollo Go operates. Initially, Hubei and Guangdong dominated online posting volume, but by July, Guangdong, Beijing, and international regions had overtaken Hubei. Attitudes varied significantly among provinces, with Xinjiang and Qinghai showing optimism and Tibet and Gansu expressing concerns about the impact on traditional taxi services. Sentiment analysis revealed that positive comments focused on technology applications and personal experiences, while negative comments centered on job displacement and safety concerns. In summary, this study highlights the divergence in public perceptions of autonomous ride-hailing services, providing valuable insights for planners, policymakers, and service providers. The model is published on Hugging Face at https://huggingface.co/wsqstar/bert-finetuned-weibo-luobokuaipao and the repository on GitHub at https://github.com/GIStudio/trb2024.
Paper Structure (11 sections, 17 figures, 6 tables)

This paper contains 11 sections, 17 figures, 6 tables.

Table of Contents

  1. Introduction
  2. Experimental Data
  3. Data Cleaning
  4. Data Processing
  5. Study Site
  6. Methodology
  7. Model Results & Analysis
  8. Temporal Features Analysis
  9. Spatial Features Analysis
  10. Sentiment Analysis
  11. Conclusion and Discussion

Figures (17)

  • Figure 1: Description of the amount of data used in each phase.
  • Figure 2: Operating conditions of Apollo Go in different regions.
  • Figure 3: Outline of the methodology used in this study, including steps for data crawling, data cleaning, data labeling, fine-tuning, sentiment classification, and data analysis.
  • Figure 4: Weekly discussion trend from the year of 2024, with a focus on July which begins in the 27th week. Data for this analysis is collected up to July 14th.
  • Figure 5: Distribution of different attitudes.
  • ...and 12 more figures