Text Data Analysis for Advertisement Recommendation System Using Multi-label Classification of Machine Learning

Abstract

Everyone today can access the streaming content on their mobile phones, laptops very easily and video has been a very important and popular content on the internet. Nowadays, people are making their content and uploading it on the streaming platforms so the size of the video dataset became massive compared to text, audio and image datasets. So, providing advertisements on the video related to the topic of video will help to boost business. In this proposed system the title and description of video will be taken as input to classify the video using a natural language processing text classification method. Aim of Natural Language Processing is to solve the text classification problem by analyzing the contents of text data and decide its category. The proposed system would extract features from videos like title, description, and hashtags based on these extracted features we intend producing classification labels with the use of multi-label classification models. Analyzing produced labels concerning advertisement datasets we intend to provide advertisements on the video related to the topic of the video.