Impact of Chatbots on User Experience and Data Quality on Citizen Science Platforms

Citizen science (CS) projects, which engage the general public in scientific research, often face challenges in ensuring high-quality data collection and maintaining user engagement. Recent advancements in Large Language Models (LLMs) present a promising solution by providing automated, real-time assistance to users, reducing the need for extensive human intervention, and offering instant support. The CS project Les Herbonautes, dedicated to mass digitization of the French National Herbarium, serves as a case study for this paper, which details the development and evaluation of a network of open source LLM agents to assist users during data collection. The research involved the review of related work, stakeholder meetings with the Muséum National d’Histoire Naturelle, and user and context analyses to formalize system requirements. With these, a prototype with a user interface in the form of a chatbot was designed and implemented using LangGraph, and afterward evaluated through expert evaluation to assess its effect on usability and user experience (UX). The findings indicate that such a chatbot can enhance UX and improve data quality by guiding users and providing immediate feedback. However, limitations due to the non-deterministic nature of LLMs exist, suggesting that workflows must be carefully designed to mitigate potential errors and ensure reliable performance.