Evaluating responses by ChatGPT to farmers’ questions on irrigated rice cultivation in Nigeria
The limited number of agricultural extension agents (EAs) in sub-Saharan Africa limits farmers’ access to extension services. Artificial intelligence (AI) assistants could potentially aid in providing answers to farmers’ questions. The objective of this study was to evaluate the ability of an AI cha...
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Language: | Inglés |
| Published: |
Research Square Platform LLC
2023
|
| Subjects: | |
| Online Access: | https://hdl.handle.net/10568/136087 |
| _version_ | 1855543263431229440 |
|---|---|
| author | Ibrahim, Ali Senthilkumar, Kalimuthu Saito, Kazuki |
| author_browse | Ibrahim, Ali Saito, Kazuki Senthilkumar, Kalimuthu |
| author_facet | Ibrahim, Ali Senthilkumar, Kalimuthu Saito, Kazuki |
| author_sort | Ibrahim, Ali |
| collection | Repository of Agricultural Research Outputs (CGSpace) |
| description | The limited number of agricultural extension agents (EAs) in sub-Saharan Africa limits farmers’ access to extension services. Artificial intelligence (AI) assistants could potentially aid in providing answers to farmers’ questions. The objective of this study was to evaluate the ability of an AI chatbot assistant (ChatGPT) to provide quality responses to farmers’ questions. We compiled a list of 32 questions related to irrigated rice cultivation from farmers in Kano State, Nigeria. Six EAs from the state were randomly selected to answer these questions. Their answers, along with those of ChatGPT, were assessed by four evaluators in terms of quality and local relevancy. Overall, chatbot responses were rated significantly higher quality than EAs’ responses. Chatbot responses received the best score three times as often as the EAs’ (40% vs. 13%). The evaluators preferred chatbot responses to EAs in 78% of cases. The topics for which the chatbot responses received poorer scores than those by EAs included planting time, seed rate, and fertilizer application rate and timing. In conclusion, while the chatbot could offer an alternative source for providing agricultural advisory services to farmers, incorporating site-specific input rate-and-timing agronomic practices into AI assistants is critical for their direct use by farmers. |
| format | Preprint |
| id | CGSpace136087 |
| institution | CGIAR Consortium |
| language | Inglés |
| publishDate | 2023 |
| publishDateRange | 2023 |
| publishDateSort | 2023 |
| publisher | Research Square Platform LLC |
| publisherStr | Research Square Platform LLC |
| record_format | dspace |
| spelling | CGSpace1360872024-11-13T09:00:15Z Evaluating responses by ChatGPT to farmers’ questions on irrigated rice cultivation in Nigeria Ibrahim, Ali Senthilkumar, Kalimuthu Saito, Kazuki artificial intelligence cultivation irrigated rice nigeria farmer participation The limited number of agricultural extension agents (EAs) in sub-Saharan Africa limits farmers’ access to extension services. Artificial intelligence (AI) assistants could potentially aid in providing answers to farmers’ questions. The objective of this study was to evaluate the ability of an AI chatbot assistant (ChatGPT) to provide quality responses to farmers’ questions. We compiled a list of 32 questions related to irrigated rice cultivation from farmers in Kano State, Nigeria. Six EAs from the state were randomly selected to answer these questions. Their answers, along with those of ChatGPT, were assessed by four evaluators in terms of quality and local relevancy. Overall, chatbot responses were rated significantly higher quality than EAs’ responses. Chatbot responses received the best score three times as often as the EAs’ (40% vs. 13%). The evaluators preferred chatbot responses to EAs in 78% of cases. The topics for which the chatbot responses received poorer scores than those by EAs included planting time, seed rate, and fertilizer application rate and timing. In conclusion, while the chatbot could offer an alternative source for providing agricultural advisory services to farmers, incorporating site-specific input rate-and-timing agronomic practices into AI assistants is critical for their direct use by farmers. 2023-12-04 2024-01-02T03:21:11Z 2024-01-02T03:21:11Z Preprint https://hdl.handle.net/10568/136087 en Open Access application/pdf Research Square Platform LLC Ibrahim, Ali, Kalimuthu Senthilkumar, and Kazuki Saito (2023). Evaluating responses by ChatGPT to farmers’ questions on irrigated rice cultivation in Nigeria. Research Square [preprints]: 18 p. |
| spellingShingle | artificial intelligence cultivation irrigated rice nigeria farmer participation Ibrahim, Ali Senthilkumar, Kalimuthu Saito, Kazuki Evaluating responses by ChatGPT to farmers’ questions on irrigated rice cultivation in Nigeria |
| title | Evaluating responses by ChatGPT to farmers’ questions on irrigated rice cultivation in Nigeria |
| title_full | Evaluating responses by ChatGPT to farmers’ questions on irrigated rice cultivation in Nigeria |
| title_fullStr | Evaluating responses by ChatGPT to farmers’ questions on irrigated rice cultivation in Nigeria |
| title_full_unstemmed | Evaluating responses by ChatGPT to farmers’ questions on irrigated rice cultivation in Nigeria |
| title_short | Evaluating responses by ChatGPT to farmers’ questions on irrigated rice cultivation in Nigeria |
| title_sort | evaluating responses by chatgpt to farmers questions on irrigated rice cultivation in nigeria |
| topic | artificial intelligence cultivation irrigated rice nigeria farmer participation |
| url | https://hdl.handle.net/10568/136087 |
| work_keys_str_mv | AT ibrahimali evaluatingresponsesbychatgpttofarmersquestionsonirrigatedricecultivationinnigeria AT senthilkumarkalimuthu evaluatingresponsesbychatgpttofarmersquestionsonirrigatedricecultivationinnigeria AT saitokazuki evaluatingresponsesbychatgpttofarmersquestionsonirrigatedricecultivationinnigeria |