EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Explainable Artificial Intelligence with Hybrid Ensemble Learning-Based Automated Code Comprehension Prediction

Bharat Babaso Mane, Rathnakar Achary

Engineering, Technology & Applied Science Research · 11.08.2026 · 16 (4) · 37326-37331

DOI: 10.48084/etasr.19084 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Engineering, Technology & Applied Science Research, online erschienen am 11.08.2026. Verfasst von Bharat Babaso Mane und 1 weiteren Autor:innen. Die Arbeit nennt 16 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Code comprehension prediction is an interesting research area in software engineering, which employs Artificial Intelligence (AI) and Machine Learning (ML) algorithms to assess how easily a programmer can understand a piece of code. To ensure precise classification models, the preceding analysis mainly relies on handcrafted features. However, manual feature engineering is labor-intensive and can acquire only partial information about the source code, limiting model performance. Recently, many Deep Learning (DL)–based code readability classification approaches have been presented. This paper presents an Explainable Code Readability Classification using Vector Representations and Majority Voting-Based Ensemble Learning (ECRVR-MVEL) approach. The model initially preprocesses the input code and then uses CodeBERT to transform it into vector representations. For classification, a Weighted Majority Voting Ensemble (WMVE) integrates a Graph Convolutional Network (GCN), a Deep Belief Network (DBN), and a Bidirectional Temporal Convolutional Network (Bi-TCN). In addition, Nadam is applied to optimize the model and improve performance. Finally, Local Interpretable Model-agnostic Explanations (LIME) is utilized to visualize the interpretability and ensure transparency. An extensive evaluation to determine the performance of the ECRVR-MVEL model on Python and C++ datasets demonstrates its promising results over existing methods.

Zitieren

APA

Mane, B. B., & Achary, R. (2026). Explainable Artificial Intelligence with Hybrid Ensemble Learning-Based Automated Code Comprehension Prediction. Engineering, Technology & Applied Science Research, 16(4), 37326-37331. https://doi.org/10.48084/etasr.19084

Vancouver

Mane BB, Achary R. Explainable Artificial Intelligence with Hybrid Ensemble Learning-Based Automated Code Comprehension Prediction. Engineering, Technology & Applied Science Research. 2026;16(4):37326-37331. doi:10.48084/etasr.19084

BibTeX
@article{Mane2026,
  author = {Mane, Bharat Babaso and Achary, Rathnakar},
  title = {Explainable Artificial Intelligence with Hybrid Ensemble Learning-Based Automated Code Comprehension Prediction},
  journal = {Engineering, Technology & Applied Science Research},
  year = {2026},
  volume = {16},
  number = {4},
  pages = {37326--37331},
  doi = {10.48084/etasr.19084}
}
Kostenlos starten →