In Machine Learning, Opinion mining is a type of text analysis technique that uses computational linguistics and natural language processing approaches to identify and extract opinions within the text automatically. It also determines the polarity of the text, such as positive, negative, or neutral. The main goal of opinion mining is the process of detecting, extracting, and classifying data in the sample. The task of opinion mining is categorized into a series of steps such as dataset acquisition, opinion identification, aspect extraction, classification, report summary, and evaluation. Support Vector Machines, Naive Bayes, and Maximum Entropy are the most commonly used machine learning algorithms for opinion mining. The most popular applications of opinion mining marketing research, product and services, financial services, and health care.
• Opinion mining covers broad areas of applications involving commercial product areas, politics area, stock market, and stock forecast.
• Selecting appropriate machine learning techniques for classifying sentiments or opinions becomes a critical step in opinion mining.
• The analysis of emotions at the level of the concept, because of its activities beyond the other three levels, has recently attracted the attention of researchers. Using different approaches and combining them at the conceptual level can be further investigated in the future.