Discovering Undisclosed Paid Partnership on Social Media via Aspect-Attentive Sponsored Post Learning

The transparency issue of sponsorship disclosure in social media advertising posts has become a significant problem in influencer marketing. Despite the fact that the Federal Trade Commission (FTC) strongly urges influencers to comply with the regulations governing sponsorship disclosure, a considerable number of influencers fail to disclose sponsorship properly in paid advertisements. The absence of sponsorship information in paid social media posts can cause consumers to lose trust in influencers and brands, which in turn has a negative impact on the influencer marketing industry. In this paper, we propose a learning-to-rank based model, Sponsored Post Detector (SPoD), to detect sponsorship of social media posts by learning various aspects of the posts such as text, image, and the social relationship among influencers and brands. More precisely, we exploit image objects and contextualized information to obtain the representations of the posts and also utilize Graph Convolutional Networks (GCNs) on a network which consists of influencers, brands, and posts with embed social media attributes. We then apply attention mechanism over different aspects of the posts to utilize more important features for discovering undisclosed sponsorship. We further optimize the model by conducting manifold regularization based on temporal information and mentioned brands in posts. The extensive studies and experiments are conducted on sampled real-world Instagram datasets containing 1,601,074 posts, which mention 26,910 brands, published over 6 years by 38,113 influencers. Our experimental results demonstrate that SPoD significantly outperforms the existing baseline methods in discovering sponsored posts on social media. The in-depth analysis further reveals that text features play an important role in detecting paid partnership and GCN features outstandingly improve the overall ranking performance. To facilitate further research, we plan to release the proposed model and the dataset as the benchmark. We believe that SPoD can be practically used by stakeholders of influencer marketing including influencers, brands, and the FTC to keep transparency in the influencer marketing industry, and also utilized by social media platforms to alert users who are not aware of sponsorship disclosing.