Public opinion evaluation on social media platforms: a case study of High Speed 2 (HS2) rail infrastructure project

Abstract

Public opinion evaluation is becoming increasingly significant in infrastructure project assessment. The inefficiencies of conventional evaluation approaches can be improved with social media analysis. Posts about infrastructure projects on social media provide a large amount of data for assessing public opinion. This study proposed a hybrid model which combines pre-trained RoBERTa and gated recurrent units for sentiment analysis. We selected the United Kingdom railway project, High Speed 2 (HS2), as the case study. The sentiment analysis showed the proposed hybrid model has good performance in classifying social media sentiment. Furthermore, the study applies latent Dirichlet allocation topic modelling to identify key themes within the tweet corpus, providing deeper insights into the prominent topics surrounding the HS2 project. The findings from this case study serve as the basis for a comprehensive public opinion evaluation framework driven by social media data. This framework offers policymakers a valuable tool to effectively assess and analyse public sentiment.