Sentiment analysis for the construction industry : a case study of Weibo in China

Construction industry is a labor-intensive industry. Sentiment or mood of participants in the construction industry is a key issue in this business. To analyze this issue, using traditional ways such as questionnaire survey to collect data is both time- and cost-consuming. Recently, with the rapid development of social media services, data can be collected and extracted for sentiment analysis to provide officials and managers with fresh perspectives on participants in the construction management. In this paper, a sentiment analysis systematic framework is proposed. This system collected user messages from social media sites, establishes and compare different clusters emotion dictionaries by time duration and location. This paper generated valuable information and knowledge in the construction domain. As an initial trial, this study selected social media of Weibo because of its wide usage in China. Four clusters which include construction workers, construction companies, construction unions, and construction media were analyzed. For each user, the crawler is used to collect the Weibo messages from his/her Web page. On average, there are 135 messages collected for each user. This research then analyzed these data in the following aspects to dig out sentiments behind data: hourly, daily, monthly, and locations. Detailed findings, benefits and barriers to incorporating social media data analytics in the construction industry, along with future research, were discussed. This paper benefits the academia by testing an alternative way of studying the construction population, which further will help decision makers better understand the real situations of the construction industry.