PROJECT TITLE :

Public Interest Analysis Based on Implicit Feedback of IPTV Users - 2017

ABSTRACT:

Modern information systems create it increasingly simple to realize more insight into the general public interest, which is changing into a lot of and additional necessary in numerous public and company activities and processes. The disadvantage of existing analysis that focuses on mining the data from social networks and online communities is that it does not uniformly represent all population teams and that the content can be subjected to self-censoring or curation. In this paper, we propose and describe a framework and a technique for estimating public interest from the implicit negative feedback collected from the Web protocol tv (IPTV) audience. Our analysis focuses totally on the channel modification events and their match with the content info obtained from closed captions. The presented framework relies on concept modeling, viewership profiling, and combines the implicit viewer reactions (channel changes) into an interest score. The proposed framework addresses each above-mentioned disadvantages or issues. It's ready to cover a abundant broader population, and it can detect even minor variations in user behavior. We have a tendency to demonstrate our approach on a large pseudonymized real-world IPTV dataset provided by an ISP, and show how the results correlate with totally different trending topics and with parallel classical long-term population surveys.