Proceedings of the 2025 10th International Conference on Financial Innovation and Economic Development (ICFIED 2025)

<Previous Article In Volume
Next Article In Volume>

A Study of ChatGPT Continuous Usage Intention Based on Random Forest and SMOTE Algorithms

Authors
Jiarui Fan1, *
1Beijing Jiaotong University, Beijing, China
*Corresponding author. Email: fanjiaruiii@outlook.com
Corresponding Author
Jiarui Fan
Available Online 5 May 2025.
DOI
10.2991/978-94-6463-702-1_61How to use a DOI?
Keywords
Artificial Intelligence; Influencing Factors; Random Forest; SMOTE Algorithm
Abstract

Today, we have transcended the traditional information age and shifted to the era driven by artificial intelligence. And the technology of domestic large language models such as Wenxin Yiyan is still maturing, and global user adoption is still relatively low. To further develop and enhance domestic large language models and gradually narrow the gap with internationally leading models, this paper explores the factors influencing users’ willingness to continuously engage with ChatGPT by establishing a random forest model and utilizing the SMOTE algorithm for model optimization. After implementing the model, the recall of the training set increased from 0.88 to 1.00, and the recall of the test set improved from 0.92 to 1.00, indicating a significant enhancement. In the importance ranking of various factors impacting the continuous use of ChatGPT, three most critical elements identified were whether ChatGPT meets localization needs, the availability of community support and resource richness, and the presence of a user-friendly interface. This provides valuable insights for the further development and refinement of domestic large language models.

Copyright
© 2025 The Author(s)
Open Access
Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

<Previous Article In Volume
Next Article In Volume>
Volume Title
Proceedings of the 2025 10th International Conference on Financial Innovation and Economic Development (ICFIED 2025)
Series
Advances in Economics, Business and Management Research
Publication Date
5 May 2025
ISBN
978-94-6463-702-1
ISSN
2352-5428
DOI
10.2991/978-94-6463-702-1_61How to use a DOI?
Copyright
© 2025 The Author(s)
Open Access
Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Cite this article

risenwbib
TY  - CONF
AU  - Jiarui Fan
PY  - 2025
DA  - 2025/05/05
TI  - A Study of ChatGPT Continuous Usage Intention Based on Random Forest and SMOTE Algorithms
BT  - Proceedings of the 2025 10th International Conference on Financial Innovation and Economic Development (ICFIED 2025)
PB  - Atlantis Press
SP  - 580
EP  - 586
SN  - 2352-5428
UR  - https://doi.org/10.2991/978-94-6463-702-1_61
DO  - 10.2991/978-94-6463-702-1_61
ID  - Fan2025
ER  -