학술논문
Ad analysis using machine learning: Classifying and recommending advertisements for a given category of videos, using machine learning
Document Type
Conference
Source
2017 International Conference on Energy, Communication, Data Analytics and Soft Computing (ICECDS) Energy, Communication, Data Analytics and Soft Computing (ICECDS), 2017 International Conference on. :2434-2437 Aug, 2017
Subject
Language
Abstract
In this paper we analyze and attempt to make video advertisements being displayed more relevant to the content of video being watched. Ads can be made more precise, in order to seek the user's attention. The right recommendation of ads, based on the content of the video viewed by a consumer, can prove to be a win-wins situation for the advertiser and the consumer. This may also help improve the sales of a product. Here we assume we already have the content that the consumer views, classified based on attributes. These attributes we try and match with the content of the video, which we analyze using edge, grey-scale and gradient detection algorithms for video. And speech detection algorithms for audio of the video. Hence in this paper we present an approach to how we could recognize the intent of an advertisement.