Social media is the new knowledge hub for all age groups. It has become a platform to express sentiments in the form of opinions and reviews on almost everything- movies, brands, product, social – activities and so on. The reviews or opinions can be positive or negative and analyzing the same is known as ‘Sentiment Analysis’. Therefore, analyzing the comments and reviews is something that an organization cannot afford to miss.
Importance of Sentiment Analysis
Most purchase decisions in the virtual world are made after going through what influential reviewers and peers have to say about the product/service. This is the reason why the companies are now forced to see and analyze what people are talking about them on the web. From the company’s perspective, the reviews and comments become very crucial. Therefore, analyzing the comments and reviews is something that an organization cannot afford to miss.
But, what are these comments or the reviews collectively called?
These comments, opinions and reviews are known as “sentiment data” and the task of identifying if the comments and the reviews are positive or negative is known as “sentiment data analysis” or “sentiment analysis”
Methods of Sentiment Analysis
- Data Collection
Consumers usually express their sentiments on public forums like the blogs, discussion boards, product reviews as well as on their private logs – Social network sites like Facebook and Twitter. Opinions and feelings are expressed in different way, with different vocabulary, context of writing, usage of short forms and slang, making the data huge and disorganized. Manual analysis of sentiment data is virtually impossible. Therefore, special programming languages like ‘R’ are used to process and analyze the data.
- Text Preparation
Text preparation is nothing but filtering the extracted data before analysis. It includes identifying and eliminating non-textual content and content that is irrelevant to the area of study from the data.
- Sentiment Detection
At this stage, each sentence of the review and opinion is examined for subjectivity. Sentences with subjective expressions are retained and that which conveys objective expressions are discarded. Sentiment analysis is done at different levels using common computational techniques like Unigrams, lemmas, negation and so on.
- Sentiment Classification
Sentiments can be broadly classified into two groups, positive and negative. At this stage of sentiment analysis methodology, each subjective sentence detected is classified into groups-positive, negative, good, bad, like, dislike.
- Presentation of Output
The main idea of sentiment analysis is to convert unstructured text into meaningful information. After the completion of analysis, the text results are displayed on graphs like pie chart, bar chart and line graphs.