AI chatbot system for educational institutions
This project presents the design and development of an advanced chatbot system powered by deep learning algorithms for intent classification. The chatbot's primary goal is to facilitate effective communication and support for users, particularly students inquiring about admission processes....
| Main Author: | |
|---|---|
| Format: | Final Year Project / Dissertation / Thesis |
| Published: |
2023
|
| Subjects: | |
| Online Access: | http://eprints.utar.edu.my/6022/ http://eprints.utar.edu.my/6022/1/fyp_IB_2023_THH.pdf |
| Summary: | This project presents the design and development of an advanced chatbot system
powered by deep learning algorithms for intent classification. The chatbot's primary
goal is to facilitate effective communication and support for users, particularly students
inquiring about admission processes. Leveraging recurrent neural network (RNN)
models, the chatbot demonstrates its proficiency in understanding and responding to
natural language queries. Through extensive training, the model achieves an impressive
86% accuracy on unseen data, affirming its robustness and adaptability. The chatbot's
capabilities extend to speech recognition, document uploads, and appointment
management, enhancing its usability and accessibility. Users can seamlessly apply for
programs, check application statuses, and schedule campus visits, all while enjoying a
user-friendly experience. In addition, the system's mobile responsiveness further
ensures uninterrupted interactions across various devices. Despite facing challenges
such as data insufficiency and overfitting during implementation, innovative solutions
like data augmentation and Batch Normalization are employed to significantly improve
model performance. The project's comprehensive evaluation, including user feedback
and adherence to usability heuristics, reaffirms the chatbot's effectiveness and
reliability. |
|---|