A Deep Convolutional Neural Network Model to Predict Consumer Recommendations using Online Reviews

Detecting consumer perception using online reviews is challenging. Artificial Intelligence (AI) techniques have the potential to understand human perception. Sensing human psychology is essential for business growth and selecting products or services in emerging markets. This paper proposes a Deep Convolutional Neural Network (DCNN) model to predict recommendations using consumer-generated online reviews. It reinforces the capability of Deep Learning (DL) models to consider two aspects of online reviews, qualitative and quantitative, and their combinations to predictive recommendations. We have collected online reviews of airline passengers from Skytrax with the objective. We have implemented various Natural Language Processing (NLP) techniques to process the qualitative contents of online reviews. Furthermore, pre-processed data with ratings on different service aspects feeds the proposed DCNN model. To validate the performance of the proposed model, we have evaluated different performance evaluation parameters such as precision, F-score, recall, and accuracy. The experimental analysis demonstrates that the DCNN model outperforms traditional Machine Learning (ML) models for predictive recommendations. Our research indicates the power of online reviews in understanding consumer intentions for emerging market growth.