Using AI to Analyse Narrative Techniques in Television Advertising

Narrative is an integral part of most television advertising as it consists of the basic building blocks of the show and captivates the audience that leads to engagement. The research discussed in this paper presents the use of artificial intelligence to analyze different storytelling strategies in commercials to evaluate their effectiveness. Using techniques of natural language processing (NLP) such as RoBERTa, the research discovers discoveries regarding the structure of ads' narratives and their correlation with audiences' awareness and emotion, as well as click-through rates. The dataset of the study is used to Analyzed the emotional appeal, humor, suspense, and informative narratives on a dataset of television commercials According to their findings, ads that are emotionally compelling earn the highest viewer engagement and informative ads suffer from higher drop-off rates. In parallel, deep analysis of sentiments around these categories shows that ads which benefit from either humor or emotional elements also garner more favorable responses than other categories. These results highlight the RoBERTa model's role in optimizing advertising tactics to help marketers create more persuasive and effective narratives. This illustrates the usefulness of automated media analysis, a growing field that has been made possible by tools like <tex xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">$A I$</tex> and big data, particularly for advertising efforts.