• MR.M.V.Subba Rao
• A.N.V.Hari Charan
• B.Naveen Eswar
• B. Nagendra Babu
• Ch.Sai Sri Harshitha

The rapid proliferation of multimedia content across digital platforms has increased the demand for automated tools capable of efficiently analyzing and moderating video content. This paper presents a multi-modal deep learning framework designed for real-time detection, analysis, and classification of inappropriate video content. The system integrates cutting-edge technologies, including YOLOv8 for object detection, Librosa for audio feature extraction, and the Natural Language Toolkit (NLTK) for sentiment analysis. By utilizing MoviePy for video and audio processing, alongside Google Speech Recognition for speech-to-text conversion, the framework offers comprehensive analysis by combining visual, audio, and textual modalities. The proposed system demonstrates high accuracy and computational efficiency, making it suitable for real-time applications in video content moderation across diverse platforms. This research highlights the potential of multi-modal deep learning frameworks in improving content safety and enhancing user experience on digital platforms. Keywords: Content Moderation, YOLOv8, Multi-modal Analysis, Deep Learning, Speech Recognition, Librosa, Real-time Detection.

"DEEP LEARNING BASED APPROACH FOR INAPPROPIRIATE CONTENT AND CLASSIFICATION OF VIDEOS", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.12, Issue 3, page no.i703-i712, March-2025, Available :http://www.jetir.org/papers/JETIR2503895.pdf

"DEEP LEARNING BASED APPROACH FOR INAPPROPIRIATE CONTENT AND CLASSIFICATION OF VIDEOS", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.12, Issue 3, page no. ppi703-i712, March-2025, Available at : http://www.jetir.org/papers/JETIR2503895.pdf