This repository contains the implementation for the paper titled RCD: Relation Map Driven Cognitive Diagnosis for Intelligent Education Systems, published at SIGIR'2021. [Paper][Presentation Video]

Authors: Weibo Gao, Qi Liu et al.

Email: [email protected]

• 🔈RCD has been used in the 'Learning & Practice' business of the HUAWEI Educational Center APP, since 2022.

• Torch version: '1.7.1'
• DGL version: '0.6.1'

To run the codes using the Junyi dataset:

1. Navigate to the code directory:

   cd RCD/RCD
   

2. Create two folders '/model' and '/result':

   mkdir model
   mkdir result
   

3. Build exercise-concept correlation local map:

   python build_k_e_graph.py
   

4. Build student-exercise interaction local map:

   python build_u_e_graph.py
   

5. Train and test RCD model:

   python main.py
   

Note: Exercise-concept correlation local map and student-exercise interaction local map can be constructed by running build_k_e_graph.py and build_u_e_graph.py respectively.

• log_data.json: Student exercising records. Source
• train_set.json: Data file for training.
• test_set.json: Data file for testing.
• graph/K_Directed.txt: Prerequisite relation from concept dependency local map, where each line is a prerequisite relation from the concept dependency local map: precursor_concept_ID\t succeed_concept_ID.
• graph/K_Undirected.txt: Similarity relation from concept dependency local map, where each line is a similarity relation from concept dependency local map: concept_ID\t similar_concept_ID.

Note: Concept dependency local map construction details are provided in the paper.

• log_data.json: Student exercising records.

• Leveraging Transferable Knowledge Concept Graph Embedding for Cold-Start Cognitive Diagnosis (SIGIR'2023). [Paper][Code][Presentation Video]
• Zero-1-to-3: Domain-level Zero-shot Cognitive Diagnosis via One Batch of Early-bird Students towards Three Diagnostic Objectives (AAAI'2024). [Paper][Code]

Please cite this paper if you use our codes. Thanks!

@inproceedings{gao2021rcd,
  title={RCD: Relation map driven cognitive diagnosis for intelligent education systems},
  author={Gao, Weibo and Liu, Qi and Huang, Zhenya and Yin, Yu and Bi, Haoyang and Wang, Mu-Chun and Ma, Jianhui and Wang, Shijin and Su, Yu},
  booktitle={Proceedings of the 44th international ACM SIGIR conference on research and development in information retrieval},
  pages={501--510},
  year={2021}
}