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{170065,
        author = {Krunal Kamble and Amol Patil and Swapnil Darphale},
        title = {Toxic Comments And Image Classifier},
        journal = {International Journal of Innovative Research in Technology},
        year = {2025},
        volume = {11},
        number = {6},
        pages = {3949-3954},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=170065},
        abstract = {With the emergence of online platforms, it has become more crucial to have in place mechanisms to recognize and stop harmful content from materializing in an effort to make digital spaces safer. This paper presents the concept of "Toxic Comments Classifier": a powerful machine learning model for commenting on the toxicity of comments in both text and image modalities. By using advanced Natural Language Processing (NLP) techniques and algorithms along with the Term Frequency-Inverse Document Frequency (Tf-Idf) approach, it evaluates and analysis the toxicity percentage in the input data. Furthermore, OCR is used to extract and process text data embedded in images to further extend its applicability. There is huge scope for utilizing this technology to improve automated content moderation processes to help platforms easily identify toxic content and, therefore promote healthier user-interactions. The classifier has shown great accuracy and scalability in its results; this holds practical implications for real-world deployment.},
        keywords = {},
        month = {March},
        }