Sentiment analysis on images using convolutional neural networks based Inception-V3 transfer learning approach

Abstract

Sentiment analysis has become a precious tool for businesses because it can be used in so many ways: to find out what customers think about products and services, to build customer relationships and loyalty, to improve customer service, and to use emotional marketing. Over the last several years, developing an end-to-end image sentiment analysis approach has significantly emphasized transfer learning methods. Deep learning algorithms have been proven to achieve remarkable outcomes across a broad spectrum of applications. Examining feelings conveyed by images is complex, but there is much space for development. A technique known as Inception-v3 that can readily focus on large portions of the body, such as a person's face, offers a significant advantage compared to the work that was done in the past. This study makes use of Inception-v3, which is a well-known deep convolutional neural network, in addition to extra deep characteristics, to increase the performance of image categorization. A CNN-based Inception-v3 architecture is employed for emotion detection and classification. The datasets CK+, FER2013, and JAFFE are used in this process. The findings are also compared with various well-known machine learning approaches, and the results obtained by the suggested model are superior. The research indicates that the proposed method can reach an accuracy level of 99.5%. The proposed approach can be used in many business applications such as Information Management, Sales, Marketing, User Interaction, Healthcare, Education, Finance, Public Monitoring, Digital PR, etc.