EEG Based Real-Time System for Video Advertisement Recommendation

Due to the innovative advancement in technology and competition in the business fields, video commercials are well known and extremely popular. As a result, analyzing the impact of these video commercials is critical before beginning marketing and promotion. Specifically, this study addresses a strategy for assessing the viability of movie commercials, which are essentially trailers, using Electroencephalogram EEG) signals captured from a Brain Computer Interface (BCI). This allows the company to consider the impact of the commercial and its value. In addition, this has a recommend system that proposes movie adverts depending on the user preferences. The particular video will be evaluated from emotion, attention and enjoyment aspect of the user. Random Forest prediction algorithm with 91.97% accuracy was used for emotion analysis, Support Vector Machine (SVM) based c-Support Vector Classifier (C-SVC) algorithm with 91.70% accuracy was used for attention analysis while using statistical approach Central Limit theorem and Empirical rule was used for enjoyment analysis to isolate particular emotion state. The preliminary results confirm that the proposed framework is yielding promising results, which is encouraging. Research on film and entertainment has potential to be expanded to many other industries, despite its current concentrate on film.