Scholarlink

Context <p>Social media data has been shown to be a valuable data source for assessing social impacts, particularly when paired with the swift progress in artificial intelligence technologies, allowing comprehensive analyses of larger datasets than is possible using conventional approaches.</p> Objectives <p>We sought to understand the social impacts of hydropower-related landscape changes based on a quasi-chronosequence of three study cases in Canada, using social media images in conjunction with machine learning to conduct image and textual analysis.</p> Methods <p>We employed the Google Cloud Vision API, a pre-trained artificial intelligence (AI)-based tool, to detect labels from over 19,000 landscape images of the relevant regions sourced from Instagram. This yielded a comprehensive set of over 188,000 labels. We used a generative probabilistic model (Latent Dirichlet allocation, an unsupervised machine learning algorithm) to create clusters based on the labels.</p> Results <p>These clusters revealed prevalent landscape features, human activities, and animate and inanimate objects—as well as which frequently co-occurred—allowing us to understand and predict some of the social impacts of the landscape changes potentially caused by hydroelectric dams and reservoirs.</p> Conclusions <p>This provides an example of integrating social media data and automated analysis tools powered by machine/deep learning into social impact assessment. Notably, such pre-trained (or “ready-to-use”) tools require minimum programming skills, benefiting scholars and practitioners who are less versed in technical domains. The insights gained from hydroelectricity case studies can also inform decisions about energy transition.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Image auto-coding tools for social impact assessment: leveraging social media data to understand human dimensions of hydroelectricity landscape changes in Canada

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2025年11月28日

查看全文
  • Yan Chen,
  • Michael Smit,
  • Kyung Young Lee,
  • Lori McCay-Peet,
  • Kate Sherren

摘要

Context

Social media data has been shown to be a valuable data source for assessing social impacts, particularly when paired with the swift progress in artificial intelligence technologies, allowing comprehensive analyses of larger datasets than is possible using conventional approaches.

Objectives

We sought to understand the social impacts of hydropower-related landscape changes based on a quasi-chronosequence of three study cases in Canada, using social media images in conjunction with machine learning to conduct image and textual analysis.

Methods

We employed the Google Cloud Vision API, a pre-trained artificial intelligence (AI)-based tool, to detect labels from over 19,000 landscape images of the relevant regions sourced from Instagram. This yielded a comprehensive set of over 188,000 labels. We used a generative probabilistic model (Latent Dirichlet allocation, an unsupervised machine learning algorithm) to create clusters based on the labels.

Results

These clusters revealed prevalent landscape features, human activities, and animate and inanimate objects—as well as which frequently co-occurred—allowing us to understand and predict some of the social impacts of the landscape changes potentially caused by hydroelectric dams and reservoirs.

Conclusions

This provides an example of integrating social media data and automated analysis tools powered by machine/deep learning into social impact assessment. Notably, such pre-trained (or “ready-to-use”) tools require minimum programming skills, benefiting scholars and practitioners who are less versed in technical domains. The insights gained from hydroelectricity case studies can also inform decisions about energy transition.