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{201157,
        author = {Srinidhi S N and Sumanth A N and Tharun V and Uday S and Dr. Thirumagal Mohan},
        title = {A Survey and Hybrid Similarity–Based Framework for Automated Publication Title Verification},
        journal = {International Journal of Innovative Research in Technology},
        year = {2026},
        volume = {12},
        number = {12},
        pages = {2391-2398},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=201157},
        abstract = {The rapid growth of print, digital, and multilingual media has significantly increased the number of publication title registration requests handled by regulatory bodies such as the Press Registrar General of India (PRGI). Traditional methods that rely on manual review or simple keyword matching are no longer sufficient, as they often fail to capture similarities arising from pronunciation differences, spelling variations, transliteration, or changes in wording. This can lead to duplication of titles, inconsistencies, and delays in the approval process. In this work, a hybrid similarity-based framework is proposed to improve the accuracy and reliability of publication title verification. The system combines phonetic similarity, string-based comparison, and semantic similarity using transformer-based sentence embeddings, allowing titles to be evaluated from multiple perspectives. In addition, rule-based validation is incorporated to ensure compliance with regulatory constraints. To further enhance usability, the system also provides a mechanism for suggesting alternative titles with lower similarity. These suggestions are generated using a combination of structured approaches and language-based generation techniques, helping users choose more unique and acceptable titles. The experimental evaluation demonstrates that the hybrid approach performs better than individual techniques, achieving an F1-score of 0.76 in representative test cases. Overall, the proposed system offers a practical and scalable solution for supporting automated decision-making in publication title verification.},
        keywords = {Hybrid AI, Phonetic Similarity, String Similarity, Semantic Similarity, Natural Language Processing, Sentence-BERT, Publication Title Verification, PRGI},
        month = {May},
        }