Scholarlink

<p>Understanding public awareness of wildlife conservation is essential for effective management, especially in developing, biodiversity-rich regions like Gilgit-Baltistan. While questionnaires are widely used to assess conservation awareness, analyzing complex formats, like our 41-question survey, can be challenging. Recent advancements in machine learning have facilitated the identification of patterns in complex survey data. To explore local conservation attitudes, we surveyed 500 respondents across 10 districts of Gilgit-Baltistan from March to June 2023 using a semi-structured questionnaire containing 41 questions across six thematic sections: socio-demographics, knowledge of endangered species, conservation opinions, economic factors, conservation experience, and views on trophy hunting. We used a self-organizing map (SOM) to identify patterns, non-metric multidimensional scaling (NMDS) to visualize them, and permutation-based analyses to identify key influencing factors. The SOM revealed four distinct attitude clusters, and NMDS showed that education and income levels were associated with conservation awareness and participation. Individuals with lower literacy and higher dependence on natural resources tended to support conservation, viewing it as an income-generating opportunity. Conversely, highly educated individuals with jobs unrelated to natural resources showed lower interest in conservation. These differences likely reflect variations in economic reliance on ecosystems, though cultural values, awareness of ecosystem services, and personal beliefs may also play roles. Notably, those relying more on natural resources favored trophy hunting over tourism as a conservation tool, likely due to its perceived financial benefits. This study highlights the importance of aligning conservation strategies with socio-economic realities, which may enhance public engagement and better address diverse community perspectives.</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

Unveiling patterns in wildlife conservation attitudes in Gilgit-Baltistan, Pakistan, using unsupervised machine learning algorithms

  • 期刊论文

  • 发表日期：

    2025年9月29日

查看全文
  • Shahab Ud Din,
  • Sungwon Hong

摘要

Understanding public awareness of wildlife conservation is essential for effective management, especially in developing, biodiversity-rich regions like Gilgit-Baltistan. While questionnaires are widely used to assess conservation awareness, analyzing complex formats, like our 41-question survey, can be challenging. Recent advancements in machine learning have facilitated the identification of patterns in complex survey data. To explore local conservation attitudes, we surveyed 500 respondents across 10 districts of Gilgit-Baltistan from March to June 2023 using a semi-structured questionnaire containing 41 questions across six thematic sections: socio-demographics, knowledge of endangered species, conservation opinions, economic factors, conservation experience, and views on trophy hunting. We used a self-organizing map (SOM) to identify patterns, non-metric multidimensional scaling (NMDS) to visualize them, and permutation-based analyses to identify key influencing factors. The SOM revealed four distinct attitude clusters, and NMDS showed that education and income levels were associated with conservation awareness and participation. Individuals with lower literacy and higher dependence on natural resources tended to support conservation, viewing it as an income-generating opportunity. Conversely, highly educated individuals with jobs unrelated to natural resources showed lower interest in conservation. These differences likely reflect variations in economic reliance on ecosystems, though cultural values, awareness of ecosystem services, and personal beliefs may also play roles. Notably, those relying more on natural resources favored trophy hunting over tourism as a conservation tool, likely due to its perceived financial benefits. This study highlights the importance of aligning conservation strategies with socio-economic realities, which may enhance public engagement and better address diverse community perspectives.