With the developing social networks, promotional campaigns for particular products or content by the form of online advertising or digital marketing, which is the hyper direct way to target and reach the users or audience. In some instances, such promotions and advertisements may redirect the users to undesirable websites or induce attacks on the user-s system due to the violation aspect of the advertiser. It also allows exaggerated information to misinform and manipulate the public in service of an attacker-s intention.
   In social networking platforms, it is mandatory to discriminate the aggressive and genuine perspective of the advertiser in posting advertisements. The reliability of online advertisements is inefficacious while focusing on advertised content. Network connectivity, range of profile activation, comments, and some other additional information of advertiser configuration are requisite to identifying trustworthiness and reliability of advertiser. Deep learning is the dominant technique in various social network analysis applications such as opinion analysis, sentiment analysis, text classification, recommender systems, structural analysis, anomaly detection, and fake news detection.
   Deep learning models learn the desirable features from a large amount of data without manual feature extraction. Thus, deep learning models estimate the authenticity of the advertiser by analyzing all the intensified information. Advertiser reliability computation in social networking is effectively performed through deep learning.