Copyright © 2026 Authors retain the copyright of this article. This article is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

@article{196882,
        author = {ABARNA V and BLESSY S and MANIKANDAN R and PRIYANKA M},
        title = {Smart Grievance Handling System Based on NLP and OCR},
        journal = {International Journal of Innovative Research in Technology},
        year = {2026},
        volume = {12},
        number = {11},
        pages = {5354-5359},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=196882},
        abstract = {Grievance redressal is an important for good governance because it helps in solving people’s complaints in a proper way. When the system works well, it gives trust between the public and the government. But in the current system, most of the petitions are handled manually, which creates a lot of problems like delays, wrong routing of complaints, and lack of accountability. Because of this, people may lose trust in the system. To solve these issues, we are proposing an AI-based grievance redressal system. In our system we use Natural Language Processing to understand and process the complaints that was given by users. We are using the RoBERTa model, this helps in understanding the meaning of the text and extracting important details from the complaint. Also, many petitions can be handwritten and scanned; we are using TrOCR to convert the image-based complaint into text. The processing of complaint was done, then the system will classify the complaints and send them to the correct department using techniques like text classification and NER. We are also providing an admin dashboard to manage all the complaints easily and an analytics dashboard to view reports and insights. This system makes the process faster, more accurate, and more transparent.},
        keywords = {Named Entity Recoginition (NER), Natural Language processing (NLP), Roberta (Transformer for NLP), Tokenization, TrOCR},
        month = {April},
        }