Understanding #WorldEnvironmentDay User Opinions in Twitter: A Topic-Based Sentiment Analysis Approach

Int J Environ Res Public Health. 2018 Nov 13;15(11):2537. doi: 10.3390/ijerph15112537.

Abstract

The main objective of this exploratory study is to identify the social, economic, environmental and cultural factors related to the sustainable care of both environment and public health that most concern Twitter users. With 336 million active users as of 2018, Twitter is a social network that is increasingly used in research to get information and to understand public opinion as exemplified by Twitter users. In order to identify the factors related to the sustainable care of environment and public health, we have downloaded n = 5873 tweets that used the hashtag #WorldEnvironmentDay on the respective day. As the next step, sentiment analysis with an algorithm developed in Python and trained with data mining was applied to the sample of tweets to group them according to the expressed feelings. Thereafter, a textual analysis was used to group the tweets according to the Sustainable Development Goals (SDGs), identifying the key factors about environment and public health that most concern Twitter users. To this end, we used the qualitative analysis software NVivo Pro 12. The results of the analysis enabled us to establish the key factors that most concern users about the environment and public health such as climate change, global warming, extreme weather, water pollution, deforestation, climate risks, acid rain or massive industrialization. The conclusions of the present study can be useful to companies and institutions that have initiatives related to the environment and they also facilitate decision-making regarding the environment in non-profit organizations. Our findings will also serve the United Nations that will thoroughly review the 17 SDGs at the High-level Political Forum in 2019.

Keywords: #WorldEnviromentDay; Nvivo; Python; Sustainable Development Goals; Twitter; machine learning; sentiment analysis; textual analysis.

MeSH terms

  • Attitude
  • Environment*
  • Humans
  • Public Health / statistics & numerical data*
  • Public Opinion
  • Social Media / statistics & numerical data*