Abstract
With the increasing penetration of the internet, an ever-growing number of people are voicing their opinions in the numerous blogs, tweets, forums, social networking, and consumer review websites. Each such opinion has a sentiment (positive, negative, or neutral) associated with it. But the problem is that the amount of data is simply overwhelming. Methods like supervised machine learning and lexical-based approaches are available for measuring sentiments that have a huge volume of opinionated data recorded in digital form for analysis. Sentiment analysis has been used in several applications including analysis of the repercussions of events in social networks, analysis of opinions about products and services. This chapter presents sentiment analysis applications and challenges with their approaches and tools. The techniques and applications discussed in this chapter will provide a clear-cut idea to the sentiment analysis researchers to carry out their work in this field.
TopFocus Of The Article
The purpose of this chapter provides a brief description of sentiment analysis, applications and challenges with their approaches and tools of sentiment analysis.
Key Terms in this Chapter
Lexicon-Based Approach: The basic concept of this approach respites an idea that the significant part of education involves understanding and produce lexical phrases as chunks.
Rapid Miner: Rapid miner is an effective tool which allow user to perform data analysis task. In aspect-based analysis it can be used to find sentiments.
Recommendation Systems: It is provided to the users for providing their views. This system also provides the development of a great corpus.
Machine Leaning Approach: Machine learning is a subset of computer science that developed from the study of pattern acknowledgement and computational study theory in artificial intelligence.
Sentiment Analysis: Sentiment analysis is the automated mining of attitudes, opinions, and emotions from text, speech, and database sources through natural language processing.
Aspect-Based Level: The aspect-based level approach carries both the document level and the sentence level analyses.
Sentence Level: Sentence level approach goes to the sentences to determine whether the sentence communicated as positive, negative, or neutral opinion. Usually, neutral means no opinion.
Domain Specific: The main problem experienced by information retrieval and emotion analysis is the domain dependent nature of words.
Document Level: The document level approach is to classify whether the whole document expresses as positive or negative sentiment.
Pandas: It represents an open source library which provides high-level of data performance of data structures, and it involves the analysis of data for Python programming language.