Sentiment Analysis: Techniques and Applications in Indian Context
Sentiment Analysis (SA) is the computational analysis of people's attitudes, opinions, and emotions toward entities, individuals, issues, events and their attributes. The task to analyze and extract emotion/polarity is technically challenging and practically very useful. For example, businesses always want to find customer opinion about their products and services. Potential customers also wish to know the opinions of existing users before they use a service or purchase a product. With the explosive growth of social media with respect to reviews, forum discussions, blogs and social networks on the Web, it is important to analyze public opinions in these media for decision making. Various techniques have been developed to analyze the sentiments based on the nature and source of data. A technique applicable to one type of data gathered from a resource may not be applicable to the data gathered from another resource. Therefore, it is required to pre-process the data before it can be analyzed for sentiment detection. An average human reader will have difficulty in choosing relevant sites and summarizing the information and opinions contained in them. Moreover, human analysis of text information is subject to considerable biases, such as people often pay greater attention to opinions that are consistent with their own preferences. People also have difficulty in producing consistent results when the amount of information to be processed is large, owing to their mental and physical limitations. Thus automated and learned sentiment analysis systems are needed, as subjective biases and mental limitations can be overcome with an objective sentiment analysis system. In the past decade, a considerable amount of research has been done to extract sentiments. There are also numerous commercial companies that provide sentiment analysis services. In this paper, we do a literature survey on the different sentiment techniques developed in the past and their application. After that, we discuss the issues of analyzing online opinions. And then we attempt to develop an algorithm to analyze the sentiment of comments, opinions or reviews in Kannada language by target and expression extraction.