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 as...
Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-01-01
|
| Series: | Computers |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2073-431X/14/1/21 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832588786133893120 |
|---|---|
| author | Akasha-Leonie Kessel Soror Sahri Sven Groppe Jinghua Groppe Hanieh Khorashadizadeh Marc Pignal Eva Perez Pimparé Régine Vignes-Lebbe |
| author_facet | Akasha-Leonie Kessel Soror Sahri Sven Groppe Jinghua Groppe Hanieh Khorashadizadeh Marc Pignal Eva Perez Pimparé Régine Vignes-Lebbe |
| author_sort | Akasha-Leonie Kessel |
| collection | DOAJ |
| description | 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. |
| format | Article |
| id | doaj-art-998650c99ed74cc1bbd87f4c80baaa86 |
| institution | Kabale University |
| issn | 2073-431X |
| language | English |
| publishDate | 2025-01-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Computers |
| spelling | doaj-art-998650c99ed74cc1bbd87f4c80baaa862025-01-24T13:27:54ZengMDPI AGComputers2073-431X2025-01-011412110.3390/computers14010021Impact of Chatbots on User Experience and Data Quality on Citizen Science PlatformsAkasha-Leonie Kessel0Soror Sahri1Sven Groppe2Jinghua Groppe3Hanieh Khorashadizadeh4Marc Pignal5Eva Perez Pimparé6Régine Vignes-Lebbe7Institut für Informationssysteme, Universität zu Lübeck, Ratzeburger Allee 160, 23562 Lübeck, GermanyLaboratoire d’Informatique Paris Descartes, Université Paris Cité, 45 Rue des Saints-Pères, 75006 Paris, FranceInstitut für Informationssysteme, Universität zu Lübeck, Ratzeburger Allee 160, 23562 Lübeck, GermanyInstitut für Informationssysteme, Universität zu Lübeck, Ratzeburger Allee 160, 23562 Lübeck, GermanyInstitut für Informationssysteme, Universität zu Lübeck, Ratzeburger Allee 160, 23562 Lübeck, GermanyInstitut de Systématique, Evolution, Biodiversité (ISYEB), Muséum National d’Histoire Naturelle, 57 Rue Cuvier, 75005 Paris, FranceInfrastructure Récolnat, Direction Générale Déléguée Aux Collections, Muséum National d’Histoire Naturelle, 57 Rue Cuvier, 75005 Paris, FranceInstitut de Systématique, Evolution, Biodiversité (ISYEB), Muséum National d’Histoire Naturelle, 57 Rue Cuvier, 75005 Paris, FranceCitizen 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.https://www.mdpi.com/2073-431X/14/1/21Large Language Model (LLM)LLM applicationchatbotuser interfacecitizen sciencedata quality |
| spellingShingle | Akasha-Leonie Kessel Soror Sahri Sven Groppe Jinghua Groppe Hanieh Khorashadizadeh Marc Pignal Eva Perez Pimparé Régine Vignes-Lebbe Impact of Chatbots on User Experience and Data Quality on Citizen Science Platforms Computers Large Language Model (LLM) LLM application chatbot user interface citizen science data quality |
| title | Impact of Chatbots on User Experience and Data Quality on Citizen Science Platforms |
| title_full | Impact of Chatbots on User Experience and Data Quality on Citizen Science Platforms |
| title_fullStr | Impact of Chatbots on User Experience and Data Quality on Citizen Science Platforms |
| title_full_unstemmed | Impact of Chatbots on User Experience and Data Quality on Citizen Science Platforms |
| title_short | Impact of Chatbots on User Experience and Data Quality on Citizen Science Platforms |
| title_sort | impact of chatbots on user experience and data quality on citizen science platforms |
| topic | Large Language Model (LLM) LLM application chatbot user interface citizen science data quality |
| url | https://www.mdpi.com/2073-431X/14/1/21 |
| work_keys_str_mv | AT akashaleoniekessel impactofchatbotsonuserexperienceanddataqualityoncitizenscienceplatforms AT sororsahri impactofchatbotsonuserexperienceanddataqualityoncitizenscienceplatforms AT svengroppe impactofchatbotsonuserexperienceanddataqualityoncitizenscienceplatforms AT jinghuagroppe impactofchatbotsonuserexperienceanddataqualityoncitizenscienceplatforms AT haniehkhorashadizadeh impactofchatbotsonuserexperienceanddataqualityoncitizenscienceplatforms AT marcpignal impactofchatbotsonuserexperienceanddataqualityoncitizenscienceplatforms AT evaperezpimpare impactofchatbotsonuserexperienceanddataqualityoncitizenscienceplatforms AT reginevigneslebbe impactofchatbotsonuserexperienceanddataqualityoncitizenscienceplatforms |