期刊
SAFETY SCIENCE
卷 143, 期 -, 页码 -出版社
ELSEVIER
DOI: 10.1016/j.ssci.2021.105411
关键词
Construction safety; Social network analysis; Knowledge sharing; Opinion leader; Sentiment analysis
资金
- Research Grants Council of the Hong Kong Special Administrative Region, China [UGC/FDS15/E01/18]
Many studies have shown that unsafe behavior is the main cause of construction accidents, and safety education and training can effectively reduce such behaviors. Social media, as a convenient and efficient tool, can be used for knowledge sharing in construction safety. Through social network analysis and sentiment analysis, we explored the knowledge sharing on Twitter related to construction safety.
Many studies show that unsafe behavior is the main cause of construction accidents. Safety education and training are effective means to minimise people's unsafe behaviors. Apart from traditional face-to-face construction knowledge sharing, social media is a good tool because it is convenient, efficient, and widely used. We applied both social network analysis and sentiment analysis to investigate knowledge sharing on Twitter. Our study is a novel attempt to understand social structure of construction safety-related twitter networks and the opinion leaders. We selected and analyzed 6561 tweets of three users' networks on Twitter - construction safety, construction health and construction accident. We found that three networks had low density and many isolated vertices, which showed that users did not actively interact with each other. The opinion leaders in this study were mostly organizations or government agencies. The top one is cif_ireland, the Irish construction industry's representative body, the Construction Industry Federation. 3200 Tweets of the top opinion leader were analyzed through graph metrics calculation, cluster analysis, sentiment analysis, and correlation analysis. The opinion leader used Twitter as a medium to disseminate the latest safety news. Thus, we may use Twitter to stimulate people's interest on construction safety topics, share construction safety knowledge, opinions and ideas. Besides, our results showed that sentiment valence had no correlation with number of favorites or retweets. Nevertheless, there was a positive correlation between favorites and retweets.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据