International Journal of Innovative Research in Computer and Communication Engineering
ISSN Approved Journal | Impact factor: 8.771 | ESTD: 2013 | Follows UGC CARE Journal Norms and Guidelines
| Monthly, Peer-Reviewed, Refereed, Scholarly, Multidisciplinary and Open Access Journal | High Impact Factor 8.771 (Calculated by Google Scholar and Semantic Scholar | AI-Powered Research Tool | Indexing in all Major Database & Metadata, Citation Generator | Digital Object Identifier (DOI) |
| TITLE | AI Student Companion: Intelligent Chatbot Assistant for Students |
|---|---|
| ABSTRACT | The AI Student Companion is an intelligent chatbot assistant developed to provide continuous and reliable academic support to students. The system integrates Natural Language Processing (NLP) and Retrieval-Augmented Generation (RAG) to retrieve relevant academic content from a structured vector knowledge base and generate accurate, syllabus-aligned responses. Unlike traditional rule-based chatbot systems, this solution combines FAISS-powered semantic search, transformer-based emotion detection, and the Gemini 2.5 Flash large language model (LLM) to deliver context-aware, factually grounded replies. A three-way intelligent routing mechanism classifies each user query into one of three pipelines: Sentiment (emotional support), RAG (document retrieval), or LLM (general knowledge). The system further incorporates an automated event announcement processor that extracts structured event information from uploaded posters and PDFs using Gemini Vision API and OCR. The backend is built on Flask and the frontend on React with TypeScript, authenticated via Firebase, and with persistent storage via Supabase. Comprehensive testing validates the system's reliability and performance across multiple testing dimensions. |
| AUTHOR | G. VIJAYA, V. CHANDRIKA, O. VAMSI, B. JAYANTH, D. AKSHAJ, V. VENKATA NAGA SATISH Assistant Professor, Department of CSE (AI & ML), Nadimpalli Satyanarayana Raju Institute of Technology, Vishakapatnam, India Students, Department of CSE (AI & ML), Nadimpalli Satyanarayana Raju Institute of Technology, Vishakapatnam, India |
| VOLUME | 182 |
| DOI | DOI: 10.15680/IJIRCCE. 2026.1403101 |
| pdf/101_AI Student Companion Intelligent Chatbot Assistant for Students.pdf | |
| KEYWORDS | |
| References | [1] A. Vaswani et al., "Attention is all you need," in Advances in Neural Information Processing Systems (NeurIPS), 2017, pp. 5998–6008. [2] J. Devlin, M. W. Chang, K. Lee, and K. Toutanova, "BERT: Pre-training of deep bidirectional transformers for language understanding," in Proc. NAACL-HLT, 2019, pp. 4171–4186. [3] T. B. Brown et al., "Language models are few-shot learners," in Advances in Neural Information Processing Systems (NeurIPS), 2020. [4] Google DeepMind, "Gemini 2.5 Flash: Frontier intelligence built for speed," Dec. 2025. [Online]. Available: https://ai.google.dev/gemini-api/docs/models. [5] P. Lewis et al., "Retrieval-augmented generation for knowledge-intensive NLP tasks," in Advances in Neural Information Processing Systems (NeurIPS), 2020. [6] "Retrieval-augmented generation (RAG): What is there for data management researchers?" in Proc. LLM+Vector Data Workshop @ IEEE ICDE 2025, Jan. 2026, pp. 33–42. [7] J. Johnson, M. Douze, and H. Jegou, "FAISS: A library for efficient similarity search," IEEE Trans. Big Data, vol. 7, no. 3, pp. 535–547, 2019. [8] N. Reimers and I. Gurevych, "Sentence-BERT: Sentence embeddings using Siamese BERT-networks," in Proc. EMNLP, 2019. [9] S. Abinaya, K. S. Ashwin, and A. Sherly Alphonse, "Enhanced emotion-aware conversational agent," IEEE Access, vol. 13, pp. 19770–19787, 2025. [10] A. E. Almutairi, A. Y. Alsobhi, and A. M. Alshareef, "Machine learning-based sentiment analysis pipeline for evaluating service quality," Int. J. Adv. Comput. Sci. Appl., vol. 17, no. 1, Jan. 2026. [11] "Retrieval-augmented generation (RAG) chatbots for education: A survey of applications," Appl. Sci., vol. 15, no. 8, p. 4234, Apr. 2025. [12] "Leveraging a custom multi modal OCR system for marksheet data extraction," in Proc. 2024 IEEE Conf., Nov. 2024. [13] "A multimodal pipeline for clinical data extraction: Applying vision-language models to scans," in Proc. 2025 IEEE Conf., Dec. 2025. [14] R. Smith, "An overview of the Tesseract OCR engine," in Proc. 9th Int. Conf. Document Analysis and Recognition (ICDAR), 2007, pp. 629–633. [15] D. Jurafsky and J. H. Martin, Speech and Language Processing, 3rd ed. draft, Pearson, 2023. [16] S. Russell and P. Norvig, Artificial Intelligence: A Modern Approach, 4th ed., Pearson, 2021. [17] M. Grinberg, Flask Web Development: Developing Web Applications with Python, 2nd ed., O'Reilly Media, 2018. |
