Enhancing User Profile Authenticity through Automatic Image Caption Generation Using a Bootstrapping Language–Image Pre-Training Model

Generating captions automatically for images has been a challenging task, requiring the integration of image processing and natural language processing techniques. In this study, we propose a system that focuses on generating captions for online social network users’ profile images using a Bootstrapping Language–Image Pre-Training Model. Our approach leverages pre-training techniques, enabling the model to learn visual and textual representations from large datasets, which are then fine-tuned on a task-specific dataset. By utilizing this methodology, our proposed system demonstrates promising performance in generating captions for online social network users’ profile images. The model effectively combines visual and textual information to generate informative and contextually relevant captions. This can greatly enhance user engagement and personalization on social media platforms, as users’ profile images are accompanied by meaningful captions that accurately describe the content and context of the images. The proposed system shows its performance on the task of caption generation for online social network users’ profile images. Furthermore, we show that our model can be used to identify scam (fake) profiles on online social networks by generating more accurate and informative captions for real profiles than for fake ones. By leveraging the power of pre-training and bootstrapping techniques, our model showcases its potential in enhancing user experiences, improving platform security, and promoting a more trustworthy online social environment. The proposed system has the potential to improve the authenticity and trustworthiness of user profiles on online social networks.