A Review of Sentiment Semantic Analysis Technology and Progress

Sentiment computing brings some new application opportunities and technique challenges in artificial intelligence of the next generation, and it has become a fascinating research field. In this paper, the conception of sentiment computing with some core elements and feature vectors is defined, and some vital issues are proposed. Based on the theories mentioned above, the subjective content or objective content is classified by some special algorithms in the scenarios of single modal, such as text, image, audio and video data. Furthermore, how to merge these different kinds of data and to form the multimodal analysis methods for emotion detection is an important problem, and the fusion strategy is summarized in the paper. Finally, some trends about the sentiment cognition and sentiment generation are analyzed, which provides new ways for further research work.

I. Definition of Sentiment Computing

In general, we focus on subjective experience and external performance of sentiment. In details, subjective experience refers to the individual's feelings of different emotional state, and external performance refers to the behavior and action of different parts of body when the emotional state occurs. In addition, in order to research sentiment expression in physiological wake-up, Picard [1] uses wearable devices to analyze sentiment features under various stress on personal physiology and is the earliest to propose the definition of “sentiment computing”. Namely, the sentiment computing is a kind of computational science that is related to sentiment, derived from sentiment, or exerts influence on sentiment. While based on the perspective of the subjective point of view, Liu [2] defines that sentiment computing is the field of study which is used to analyze people's opinions, sentiments, evaluation, appraisals, attitudes, and emotions towards entities such as products, services, organizations, individuals, issues, events, topics, and their attributes. To sum up, sentiment computing is an interdisciplinary science, fusing cognitive psychology, Natural Language Processing, and multi-modal recognition knowledge, which mainly uses information of objective world to show the tendency, perspectives, stances and attitudes of subjective sentiment. It is a process for sorting and summarizing features such as emotional polarity, intensity, and variation tendency.