@inproceedings{phuc-etal-2026-edupulse,
    title = "{E}du{P}ulse: A Practical {LLM}-Enhanced Opinion Mining System for {V}ietnamese Student Feedback in Educational Platforms",
    author = "Phuc, Nguyen Xuan  and
      Xuan, Phi Nguyen  and
      Nguyen, Vinh-Tiep  and
      V{\u{a}}n, Th{\`i}n {\DJ}ặng  and
      Nguyen, Ngan Luu-Thuy",
    editor = {Matusevych, Yevgen  and
      Eryi{\u{g}}it, G{\"u}l{\c{s}}en  and
      Aletras, Nikolaos},
    booktitle = "Proceedings of the 19th Conference of the {E}uropean Chapter of the {A}ssociation for {C}omputational {L}inguistics (Volume 5: Industry Track)",
    month = mar,
    year = "2026",
    address = "Rabat, Morocco",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-eacl/2026.eacl-industry.25/",
    pages = "338--365",
    ISBN = "979-8-89176-384-5",
    abstract = "Opinion mining from real-world student feedback presents significant practical challenges, such as handling linguistic noise (slang, teencode) and the need for scalable and maintainable systems, which are often overlooked in academic research. This paper introduces EduPulse, a practical opinion mining system designed specifically to analyze student feedback in Vietnamese. Our application performs four opinion analysis tasks, including Sentiment Classification, Category-based Sentiment Classification, Suggestion Detection, and Opinion Summarization. We design the hybrid architecture that strategically balances performance, cost, and maintainability. This architecture leverages the robustness of Large Language Models (LLMs) for complex, noise-sensitive tasks as sentiment classification and suggestion detection, while employing a specialized, lightweight neural model for high-throughput, low-cost solutions. Our experiments show that applying the LLM-based approach achieves high robustness, justifying its operational cost by eliminating expensive retraining cycles. Furthermore, we demonstrate that our collaborative modular architecture significantly improves task performance (+7.6{\%}) compared to traditional approaches, offering a practical design for industry-focused Natural Language Processing applications."
}