International Journal of Information Technology (IJIT) – Volume 6 Issue 4, Jul-Aug 2020 ISSN: 2454-5414 www.ijitjournal.org Page 38 Agent Based Smart Influence Maintenance in Social Networks Shilpa Chavan [1] , Prof. Sarika Solanke [2] [1] MTech 2nd year student, Assistant Professors, [2] Department of Computer Science and Engineering, Deogiri Institute of Engineering and Management Studies, Aurangabad (MH), India. ABSTRACT: In different domains, like marketing, e-business, and social computing, Most existing studies focus on how to maximize positive social impact to promote product adoptions based on static network snapshots. Such approaches can only increase influence in a social network in short-term, but cannot generate sustainable or long-term effects. In this system, we will maintain long-term influence in a social network and propose an agent-based influence maintenance model, which can select influential nodes based on the current status in dynamic social networks in multiple times. Within the context of our Analysis, the experimental results shows that multiple- time seed selection is capable of achieving more constant impact than that of one-shot selection. Keywords: – Influence maintenance, influence diffusion, long-lasting influence, agent-based modeling. I. INTRODUCTION In various domains, such as e-business, marketing, and social computing. Most studies cases focus on how to increase positive social impact to stimulate product adoptions based on static network snapshots. Such approaches can only increase influence in a social network in short-term, but cannot generate sustainable or long-term effects. In this system, we will maintain long-term influence in a social network and propose an agent-based influence maintenance model, which can select influential nodes based on the current status in dynamic social networks in multiple times. Within the context of our investigation, the experimental results indicate that multiple- time seed selection is more capable of achieving more constant impact than that of one-shot selection. This System claim that influence maintenance is crucial for supporting, enhancing and assisting long-term goals in business development. The proposed approach can automatically maintain long-lasting impact and achieve influence maintenance [1]. With the prevalence and advancement of the Internet, on-line social networks have become an important and efficient channel for information propagation. The propagation relies on one of the social phenomena, i.e., social influence, indicating that one’s opinions or behaviors are affected by his or her contactable neighbours in the social network [2]. Influence message is a Prevalent and tactile portray of social influence, which ‘travels’ mostly through the network topologies via users’ sharing and posting behaviors. By leveraging the power of social influence, a great many business owners attempt to expand the market and increase the brand awareness through the ‘word-of-mouth’ effect. In recent years, influence maximization draws tremendous attention to both researchers and domain experts. Influence maximization attempts to identify a set of influential users committed to spreading a piece of influence message to their neighbours, such as adopting a product, expecting that they can propagate influence and maximize the positive impact across the entire network [3]. The selected group of influencers is called seed set, and the seeding process is named as seed selection. From a business perspective, influence maximization corresponds to short-term marketing effects, which tend to cause sudden profit spikes that rarely last [4]. Whereas, long-term marketing is typically more beneficial since it emphasizes on long-term and sustainable business goals. Specifically, long-term influence can establish brand awareness and continually produce results even years down the road; thus, without having long-term marketing strategies, shortterm success may be short-lived [5]. Motivated by this background, in this research, we aim to achieve constant impact for longterm marketing by investigating the preservation of a particular type of influential situation or status, called influence maintenance. There are many limitations for short- term (or even oneshot) influence maximization when being utilized in real business cases. First, it focuses on how to maximize the influence of one-shot investment. Based on the risk management theory and best practice [6], with the same budget, the multiple-time investment could enable a better business strategy. For example, in a stock market, very few investors purchase stocks with all the money at only one time. Second, a great many business owners intend to expand the lifespan of influence, so that the brand awareness can be enhanced and increased in the long run [7]. Influence maintenance not only cares about the quantity of users being affected but also considers constant influence impact. Influence maintenance needs to be supported by a formal influence diffusion model which possesses two attributes: (1) The model is capable of capturing the temporal feature of a social network; (2) The model can monitor the status of a particular influence. RESEARCH ARTICLE OPEN ACCESS