Few studies have mined social media platforms to assess environmental concerns. In this study, Twitter was scraped to obtain a ~140,000 tweet dataset related specifically to marine plastic pollution. The goal is to understand what kind of users profiles are tweeting and how and when they do it. In addition, topic modelling and graph theory techniques have allowed us to identify main concerns on this topic: i) impact on wildlife, ii) microplastics/water pollution, iii) estimates/reports, iv) legislation/protection, and v) recycling/cleaning initiatives. Results reveal a scarce influence of organizations involved in research and marine environmental awareness, so some guidelines are depicted that could help to adjust their communication plans. This is relevant to engage society through reliable information, change habits and reinforce sustainable behaviour. A visualization tool has been created to analyze the results over time.

很少有研究利用社交媒体平台来评估环境问题。在这项研究中，Twitter 被抓取以获得约 140,000 条专门与海洋塑料污染相关的推文数据集。目标是了解哪些用户的个人资料在发推文，以及他们如何以及何时发推文。此外，主题建模和图论技术使我们能够确定该主题的主要关注点：i) 对野生动物的影响，ii) 微塑料/水污染，iii) 估计/报告，iv) 立法/保护，以及 v) 回收/清洁举措。结果显示参与研究和海洋环境意识的组织的影响很小，因此描述了一些有助于调整其沟通计划的指南。这与通过可靠信息参与社会有关，改变习惯并加强可持续行为。已经创建了一个可视化工具来分析一段时间内的结果。