Anastasia Vangelova

Ms. Anastasia Vangelova

orcid

Research Focus & Metrics

Academic Career Length

1Year (2026-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
4 April 2026 in Applied Sciences
Verified
Journal Article
Open access
PDF file
Anastasia VangelovaAnastasia Vangelova
Anastasia Vangelova
VGVeska Gancheva
Veska Gancheva
Automated scoring of open-ended questions is an important research direction in educational technology and artificial intelligence, as manual grading is time-consuming and often subject to inter-rater variation. This paper proposes an AI-based framework for automated scoring that combines large language models (LLMs), Retrieval-Augmented Generation (RAG), analytical rubrics, and structured machine-readable output within a Moodle-supported e-learning environment. The framework is designed to support context-grounded and criterion-based evaluation by combining the student response, retrieved instructional context, and rubric-defined scoring criteria within a controlled assessment workflow. The proposed approach aims to improve the consistency, traceability, and practical applicability of automated scoring for open-ended responses. To examine its performance, an experimental study was conducted in a real university setting involving a five-task open-ended examination. AI-generated scores were compared with independent human scores using agreement, reliability, correlation, and error metrics. The results indicate a strong level of agreement between automated and expert scoring within the tested setting, together with relatively low average deviation. These findings suggest that the proposed framework has practical potential for supporting automated assessment in digital learning environments, while also highlighting the importance of careful interpretation within the scope of the experimental design.

17 June 2026 in Information
Verified
Journal Article
Open access
PDF file
Anastasia VangelovaAnastasia Vangelova
Anastasia Vangelova
AAAdelina Aleksieva-Petrova
Adelina Aleksieva-Petrova
This study investigates the role of the semantic layer as the contextual foundation of Retrieval-Augmented Automated Assessment, examining how its architecture and semantic extraction mechanism contribute to the reliability, validity, and consistency of automated assessment relative to expert judgment across diverse learning task types. The proposed system is implemented as an integrated architecture combining the Moodle e-learning platform, the n8n orchestration layer for workflow automation, and a dedicated semantic layer responsible for learning context extraction. Moodle manages assignments, rubrics, and student submissions, while automated workflows process the data and activate the Retrieval-Augmented Generation (RAG) mechanism to retrieve relevant learning content and perform automated evaluation. The experimental study was conducted on a purpose-built Moodle environment, designed to ensure full control over assessment processes, event logging, and AI system integration. Results for the full sample yielded a Spearman’s rank correlation coefficient of ρ = 0.874, indicating a very strong positive correlation between expert and automated rankings. Task-level analysis further revealed that system performance is closely tied to the degree of structure and formalizability of the learning tasks: lower agreement was observed for open-ended and interpretive tasks, while structured and logically defined tasks yielded results comparable to expert assessment. These findings provide preliminary evidence that, within the tested course context, the proposed methodology is especially suitable for tasks with clearly formulated criteria and a consistent logical structure, while also identifying directions for future improvement in more subjective and context-dependent assessment scenarios.

Verified
Journal Article
Open access
PDF file
Anastasia VangelovaAnastasia Vangelova
Anastasia Vangelova
AAAdelina Aleksieva-Petrova
Adelina Aleksieva-Petrova
The growing adoption of Generative AI in education has created opportunities to automate complex pedagogical tasks, yet reliably and scalably assessing open-ended responses remains a challenge. This study proposes and evaluates an architectural solution for integrating a Large Language Model (LLM) into Moodle, combining Retrieval-Augmented Generation (RAG) and AI agent mechanisms to enable automated grading of open-ended student responses. A Moodle instance was deployed for experimental purposes, with 32 students across Bulgarian- and English-language sections, yielding data at the student (N = 32) and task (N = 160) levels, including AI-generated and instructor-assigned scores and system processing logs. The results demonstrate that the proposed system achieves substantial reductions in grading time while maintaining high agreement with expert assessments. Bias analysis revealed minimal systematic deviation across both language groups, indicating that the system preserves assessment objectivity without consistent over- or underestimation based on language. These findings suggest that a combined RAG and agentic LLM architecture can deliver efficient, accurate, and linguistically robust automated assessment within an LMS environment, offering practical design guidelines applicable to other educational platforms and similar systems.

17 July 2026 in Engineering Proceedings
Verified
Conference Paper
Open access
PDF file
Anastasia VangelovaAnastasia Vangelova
Anastasia Vangelova
VGVeska Gancheva
Veska Gancheva
This paper presents a RAG-based architecture with a large language model for automated assessment of student responses, in which Bloom’s Taxonomy is used to structure an analytical rubric and to form a cognitive profile of the performance. The approach integrates Moodle, n8n, a vector database for semantic retrieval of relevant context, and a GPT model for criterion-based assessment. The model’s output is formed based on the student response, the RAG-extracted learning context, and a predefined rubric. The system is implemented in a real exam environment in Bulgarian and English. The results of data analysis show differentiated behavior across Bloom’s cognitive levels, with higher sensitivity in tasks related to remembering, understanding, and applying, and more conservative behavior in tasks related to evaluating and critical thinking. Expert evaluation of the automatically generated feedback confirms its clarity, usefulness, and correctness.
1

2 July 2026 in Applied Sciences
Verified
Journal Article
Open access
PDF file
Anastasia VangelovaAnastasia Vangelova
Anastasia Vangelova
VGVeska Gancheva
Veska Gancheva
Large language models (LLMs) are reshaping the automated assessment of open-ended student responses. Compared with earlier rule-based, statistical, and feature-engineered approaches, they enable a deeper interpretation of meaning, context, and argumentation. This development can be understood as a fifth generation of automated scoring systems, but it also raises a new question: not only what LLMs can do, but also how they can be deployed in education in a controlled and reliable manner. This paper presents a role-based taxonomy that distinguishes between generative LLMs used as direct virtual graders, encoder transformers used as semantic tools, and intermediate text-to-text models used in more formalized assessment tasks. It also discusses the main limitations of standalone LLM graders, including hallucinations, probabilistic instability, limited interpretability, bias, and weak grounding in domain-specific content. To address these issues, the paper presents a developed framework implemented in an integrated assessment system built on role prompting, rubric-constrained grading, Retrieval-Augmented Generation (RAG), structured machine-readable outputs, workflow orchestration, and LMS integration. The framework is further extended to multimodal assessment through vision-based evaluation of visual artifacts such as UML state diagrams. The main contribution of the paper is not only a conceptual framework, but also its realization in a working integrated system for automated assessment in a more traceable, pedagogically grounded, and institutionally reliable way.