AI Virtual Assistant for Students (Voice + NLP + Knowledge Graph)
Bibliographic record
Abstract
Abstract - The education sector increasingly relies on intelligent and personalized digital learning tools to support students in understanding academic content effectively. However, students often depend on fragmented resources such as textbooks, lecture notes, and multiple online platforms, leading to confusion, time consumption, and delayed learning outcomes. This paper proposes an AI Virtual Assistant for Students using Voice Interaction, Natural Language Processing (NLP), and Knowledge Graph-based reasoning to provide intelligent and interactive academic support. The system enables students to ask questions using voice or text and receive accurate, context-aware responses in real time. NLP techniques are used to understand user intent, while the knowledge graph organizes academic concepts in a structured and interconnected manner, allowing meaningful and conceptually linked responses. The proposed web-based system ensures scalability, accessibility, and reliable operation through secure access mechanisms and efficient response validation. By integrating intelligent conversational support with structured knowledge representation, the system enhances learning efficiency, improves conceptual understanding, and contributes to a better digital education experience. Key Words: AI Virtual Assistant, Natural Language Processing, Knowledge Graph, Semantic Search, Educational Technology, Student Learning Support
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 0.002 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.001 | 0.000 |
| Science and technology studies | 0.001 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.002 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.020 | 0.008 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".