• Rajat Singh
• Hrishikesh Radke
• Akash Gajare
• Dr.Priya Pise

Online social networks have become an important portion of the daily life of people, and more and more users now use numerous online social networks (OSNs) concurrently with diverse social media services. While most of the present work mostly sums the scattered user behaviors or features directly, there has been very small current effort to understand the cross-OSN relation from shared user behaviours. We go one step advance in this project to understand the complex characteristics of user activities and suggest a dynamic cross-OSN mining model for the organization. Dynamic user modeling is initially performed in this system to capture the sense of user interest in each OSN. A session-based factorization approach is then planned to dynamically create the cross-OSN association by informing the derived association incrementally every time a new data session arrives. We finally model a coldstart YouTube video on the basis of the resulting dynamic association. Experiments are carried out using Twitter and YouTube real-world user data. The results show the efficiency of this planned structure in capturing the fundamental relationship between various OSNs and achieving superior recommendation output for coldstarting.

Cross-OSN association, dynamic user modelling,cold start recommendation.

"YouTube Recommendation Using Twitter", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.7, Issue 4, page no.2071-2075, April 2020, Available :http://www.jetir.org/papers/JETIR2004484.pdf

"YouTube Recommendation Using Twitter", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.7, Issue 4, page no. pp2071-2075, April 2020, Available at : http://www.jetir.org/papers/JETIR2004484.pdf