A Deep Learning Approach for Video Metadata Generation and Classification
Author(s):
Dr. T. Raghunadha Reddy, P. Sreekari, J. Nikhil Kumar Reddy, V. Jyothsna
Keywords:
LSTM, Flask Framework, YouTube Videos, Natural Language Processing.
Abstract
Video information is one of the most emerging and easy ways to learn and know about anything that is going on around the world. On the internet, video material has grown in popularity influencing many parts of our life including education, entertainment, and communication. Video content is one of the most attractive ways where each and every individual attracts to the pictographic and visualization of the content which helps in easy understanding and gain of knowledge. YouTube is the prime source for generating and classifying the videos and is considered as of the most entertaining media where worldwide information is present. The main objective of this article is to generate and classify video content into different categories. We consider videos from YouTube which has subtitles. The primary goal is to extract and categorize information from videos. The procedure entails using Natural Language Processing (NLP) to extract text that may contain unwanted characters or symbols, necessitating text cleaning. The NLP is basically for analysing the relevant information. To extract important information from text, certain text pre-processing techniques such as tokenization and stemming need to be applied on the text. In this work, The YouTube URL is copied and uploaded to the front-end web page. After the URL is uploaded, the NLP process generates the subtitles of text by using the dataset which is considered for this work. The dataset contains a CSV file which contains the records where the data is pre-processed and keywords are generated. Once the pre-processing is done, the summary is generated from the retrieved text and categorized based on keywords and synonyms. The entire process is sent to the LSTM model to train and test the model for accurate output. Users can provide URLs, and the system will create a summary that is categorized appropriately. To give an interactive web-based output, this article is incorporated into the Flask framework.
Article Details
Unique Paper ID: 159758

Publication Volume & Issue: Volume 9, Issue 12

Page(s): 719 - 725
Article Preview & Download


Share This Article

Conference Alert

NCSST-2023

AICTE Sponsored National Conference on Smart Systems and Technologies

Last Date: 25th November 2023

SWEC- Management

LATEST INNOVATION’S AND FUTURE TRENDS IN MANAGEMENT

Last Date: 7th November 2023

Latest Publication

Go To Issue



Call For Paper

Volume 10 Issue 1

Last Date for paper submitting for March Issue is 25 June 2023

About Us

IJIRT.org enables door in research by providing high quality research articles in open access market.

Send us any query related to your research on editor@ijirt.org

Social Media

Google Verified Reviews

Contact Details

Telephone:6351679790
Email: editor@ijirt.org
Website: ijirt.org

Policies

Important Links

Browse Rsearch papers