In the realm of advertising, strategic placement and presentation of advertisements are crucial for attracting potential clients. Media companies employ various tactics, such as visually appealing features and vibrant colors, to capture the attention of consumers. However, achieving this objective is not always straightforward, as some advertising strategies may be perceived as irrelevant or disturbing by recipients. This Master's thesis aims to explore the relationship between audience interaction and the perception of advertisements on media platforms, with the overarching goal of enhancing advertising effectiveness and addressing ethical concerns associated with targeted advertising. To delve into this topic comprehensively, this study utilizes real-time data provided by Amedia, one of the largest media companies in Norway. Through an extensive analysis of this real-world data, the research aims to explore the correlation between audience interaction and the perception of advertisements on media platforms. This investigation involves the extraction of relevant features from advertisement images, leading to the creation of a new dataset. Concurrently, predictive machine learning models are developed to gain insights into effective advertising strategies for media companies, with a focus on personalization. Furthermore, a comprehensive user study is conducted to gain insights into user behavior within media platform advertisements. By uncovering the interplay between visual features, user behavior, and advertising effectiveness, this research contributes to improving personalized advertising strategies in the context of media companies.