Background <p>Many chemical releases are first noticed by community members, but reporting these concerns often involves considerable hurdles. Artificial Intelligence (AI)-enabled technologies, especially large language models (LLMs), can potentially reduce these barriers.</p> Objective <p>We hypothesized that AI-powered chatbots can facilitate reporting of pollution incidents through text messaging.</p> Methods <p>We created an AI-powered chatbot, “MyEcoReporter,” that enables communities to report environmental incidents to government authorities. Eschewing traditional web-based forms, users text concerns via SMS to the LLM-powered application, engaging in a natural conversation through which required information is collected. The application was built using Python, AWS Lambda, DynamoDB, and Twilio, and deployed via Serverless.</p> Results <p>This architecture allowed rapid customization for various use cases, which successfully facilitated conversations and stored structured data for formal submission.</p> Impact statement <p>MyEcoReporter showcases the potential of Artificial Intelligence/Large Language Models to create user-friendly tools that translate community environmental concerns into actionable information for reporting to government authorities.</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

MyEcoReporter: a prototype for artificial intelligence-facilitated pollution reporting

  • Weihsueh A. Chiu,
  • Galen Newman,
  • Garett Sansom,
  • Xinyue Ye,
  • Andriy Rusyn,
  • Haotian Wu,
  • Tom Winckelman,
  • Ivan Rusyn

摘要

Background

Many chemical releases are first noticed by community members, but reporting these concerns often involves considerable hurdles. Artificial Intelligence (AI)-enabled technologies, especially large language models (LLMs), can potentially reduce these barriers.

Objective

We hypothesized that AI-powered chatbots can facilitate reporting of pollution incidents through text messaging.

Methods

We created an AI-powered chatbot, “MyEcoReporter,” that enables communities to report environmental incidents to government authorities. Eschewing traditional web-based forms, users text concerns via SMS to the LLM-powered application, engaging in a natural conversation through which required information is collected. The application was built using Python, AWS Lambda, DynamoDB, and Twilio, and deployed via Serverless.

Results

This architecture allowed rapid customization for various use cases, which successfully facilitated conversations and stored structured data for formal submission.

Impact statement

MyEcoReporter showcases the potential of Artificial Intelligence/Large Language Models to create user-friendly tools that translate community environmental concerns into actionable information for reporting to government authorities.