bayesNestor

Overview

bayesNestor is a Bayesian Network implementation designed to dynamically generate personalized learning paths tailored to the unique psychological traits of each learner, aiming to optimize educational outcomes.

Installation

Ensure you are using Python 3.10 or above.

Install bayesNestor using pip:

pip install bayesnestor

Usage

from bayesnestor import Nestor
# Provide evidence for a query
QUERY_EVIDENCE = {
    "Active_Reflective_Dim": "Active",
    "Sensory_Intuitive_Dim": "Intuitive",
    "Visual_Verbal_Dim": "Visual",
    "Sequential_Global_Dim": "Global",
    "cs": "agree",
    "bfia": "disagree"}

# Example usage: generate learning paths
mynestor = Nestor()
lpath = mynestor.generate(evidence=QUERY_EVIDENCE)
print(lpath)

Examples

The "examples/" directory contains five example scripts demonstrating key functionalities of bayesNestor:

• example_access_backend_objs.py: Demonstrates how to access and utilize different backend objects.
• example_load_xmlbif.py: Provides a step-by-step guide on loading Bayesian Networks saved in XMLBIF format, ensuring model restoration and compatibility.
• example_nestor_generate_lepath.py: Walks through the process of generating personalized learning paths by using bayesNestor's inference capabilities.
• examples_model_manager.py: Illustrates how to manage and configure models by defining the network structure and parameters, enabling efficient customization and tuning.
• examples_reporting.py: Shows how to generate reports that analyze model outputs, interpret results.

Feel free to run these examples to better understand how to implement and use the package.

Authors

• Vamsi Krishna Nadimpalli - vamsi.nadimpalli@oth-regensburg.de
• Robert Maier - robert.maier@oth-regensburg.de

How to Cite

If you find bayesNestor useful in your research or projects, please consider citing it as follows:

@inproceedings{nadimpalli2025nestor,
author = {Nadimpalli, Vamsi Krishna and Maier, Robert and Ezer, Timur and Bugert, Flemming and Staufer, Susanne and Roehrl, Simon and Hauser, Florian and Grabinger, Lisa and Mottok, Juergen},
title = {Nestor: A Personalized Learning Path Recommendation Algorithm for Adaptive Learning Environments},
year = {2025},
isbn = {9798400712821},
publisher = {Association for Computing Machinery},
address = {New York, NY, USA},
url = {https://doi.org/10.1145/3723010.3723016},
doi = {10.1145/3723010.3723016},
booktitle = {Proceedings of the 6th European Conference on Software Engineering Education},
pages = {49–59},
numpages = {11},
keywords = {Machine Learning, Bayesian Network, Psychological Models, Learner-Centered environments, Personalized Learning Paths},
location = {Kloster Seeon, Germany},
series = {ECSEE '25}
}

Acknowledgements:

The Federal Ministry of Research, Technology, and Space (BMFTR) supports this work by funding the HASKI project (FKZ: 16DHBKI035).