Toddler Stunting Consulting Chatbot using Rasa Framework
| Autor: | Wiwien Hadikurniawati, Sutarto Wijono, Danny Manongga, Irwan Sembiring, Kristoko Dwi Hartomo |
|---|---|
| Jazyk: | angličtina |
| Rok vydání: | 2023 |
| Předmět: | |
| Zdroj: | Jurnal Rekayasa Elektrika, Vol 19, Iss 4 (2023) |
| Druh dokumentu: | article |
| ISSN: | 1412-4785 2252-620X |
| DOI: | 10.17529/jre.v19i4.33014 |
| Popis: | Chatbots are artificial intelligence software that can communicate with users to assist them in certain tasks or provide information. They can reduce the need for human interaction and make processes more efficient. However, when it comes to more specific tasks related to handling the problem of stunting in toddlers these services are usually unable to provide an appropriate response. Chatbots were created with the help of the Rasa framework, which was designed to adapt the various components of natural language understanding (NLU). This adjustment allows him to understand more complex questions from respondents such as those related to healthy feeding of toddlers. This research explained the use of the Rasa framework to enhance their capabilities, describe the testing and evaluation process, and present the performance results of the chatbot model in addressing the issue of stunting in toddlers. The model is then tested using a confusion matrix, precision, accuracy, and F1 score, which measures how accurate the chatbot's responses are to the user's input. The model had a precision, accuracy, and F1 score of 0.928, 0.932 and 0.930, respectively. |
| Databáze: | Directory of Open Access Journals |
| Externí odkaz: |
|