Public-Opinion Sentiment Analysis for Large Hydro Projects

Abstract

Public opinion is becoming increasingly involved in feasibility studies, construction, and post-evaluation of large hydro projects. Recently, with the rapid development of social network services, sentiment analysis can provide officials and managers with fresh perspectives on public-relation problems in project management. An effective sentiment analysis method can enable projects to gain from public participation. In this paper, a project sentiment analysis (PSA) system using a lexicon-based method is proposed. This system collects user opinions from social network sites, establishes emotion dictionaries, and builds basic rules that calculate those sentiment values embodied in a collection of messages. The Three Gorges project (TGP) was used as a case study for demonstrating the effectiveness of the proposed PSA. Sentiment analysis results show that about half (47.7%) of the collected messages expressed negative emotions towards the TGP, while the other messages were positive or neutral. The case study is of help to Chinese government and project managers in future decision-making regarding the TGP. The PSA system provides a new theoretical perspective and a practical method to assess public opinion during the whole life-cycle of a large hydro project.