Design and Development of Intelligent and Boosted Learning Framework for Brand Digital Marketing

Brand Digital marketing has opened huge avenues for brand promotions, due to the emergence of artificial intelligence (AI), and Big data analytics. Moreover, it is crucial to understand the customer's interaction for improving the strategies and optimizing marketing campaigns. Sentimental analysis is the process of identifying the customers' behaviour through texts, which widely helps in improving the process of digital marketing. In the recent times, machine learning and deep learning algorithms have played significant role on analysing the sentiments across the various digital and social platforms. But these algorithms need more enhancements in terms of high performance and computations, handling larger datasets. In this regard, the research paper proposes the novel Attention Evoked Boosted Gated recurrent Units (AE-BGRU) for analysing the sentiments across the larger datasets. The comprehensive experimentation was conducted using the Kaggle Marketing Campaigns Datasets and performance measures like accuracy, precision, recall and F1-score are calculated. To prove excellence of a proposed model, performance of the suggested boosted network was compared with other baseline architectures. Empirical outcomes demonstrates a suggested model has achieved the accuracy of 0.99, precision of 0.987, recall of 0.986 and F1-score of 0.99 and outperforms the other existing models. This research proves the strength of the optimized feedforward network is its potential to minimize overfitting, enhance generalization, and deliver a performance mechanism that guarantees efficient digital brand interaction and decision-making in significantly dynamic online settings.