Skip to main content

What is Sentimental Analysis?


Sentimental Analysis Concept

The terms sentimental analysis and idea mining first appeared in 2003. Before the 2000s, some ideas such as perspective effects, emotional adjectives, metaphor interpretations were brought forward, but the main studies were carried out later. Many nomenclatures are used in relation to Sentimental Analysis.

Some of them are as follows:

Slant examination, feeling mining, assessment extraction, assumption mining, subjectivity investigation, influence investigation, feeling examination, audit mining and so forth.
The most commonly used name is Sentimental Analysis or Emotion Analysis . But not only words are needed for emotion analysis, emotion analysis studies can be done thanks to the emojis used to express emotions. There are many emoji that people use in happiness situations, like the “☹” expression that people use in unhappiness situations. Many analysis studies have been made on these issues. For example: In the research carried out by Mohammed O. Shiha and Serkan Ayvaz, the effects of emojis used in data collected on Twitter with R language on Sentimental analysis were investigated and according to the results, they discovered that users generally use emoji in their "positive" tweets.

Research Demonstrates Improving Sentimental Analysis

According to Bing Liu, they want to know the opinions of consumers about big organizations and all business services or products in the real world, and also the consumer wants to know the opinions of the products by the current users. Due to such reasons, emotion analysis studies have developed rapidly in many organizations and workplaces, and they are gaining momentum every day.

Effect on Social Media

In addition, with the groundbreaking growth of social media, individuals and organizations began to use social media more often to make better decisions. For this reason, the huge data shared on social media gained great importance and both the consumer and the manufacturer wanted to see the meaningful results of this data, so that emotion analysis studies gained speed. For example: Nowadays, a consumer is not limited to the circle of friends or family to buy a product; To read the comments of other users, he reviews the comments on public forums or blogs and makes his own decision through the sharing of emotions.

In short, many institutions today prefer to conduct research on the web and to examine thoughts instead of public opinion polls and surveys. It is very difficult for people to do such great research manually, analyze emotions and draw detailed conclusions from all data. For this reason, Sentimental Analysis systems were created.

Research Levels Used in Sentimental Analysis

Sentimental analysis applications are used in many fields. Consumer services, health, political choices, social organizations, financial services can be given as examples.


Different research levels and grouping methods are used in SA. Thanks to these grouping methods and research levels, analysis studies were conducted. The chronological development of sentimental analysis is Document Classification first, then Text classification followed by Thought Mining and finally Emotion Analysis.

As research level, 3 different levels are used.

Document Level:

According to a document with this method, it is the method that produces a negative or positive result.

For example: According to a product review, the system checks all words and, as a result, produces a negative or positive value.

This form of analysis is not suitable for documents that compare multiple products or situations. Because, when more than one situation or product comparison is made, more than one result is expected. However, only one result is obtained with this method.

Sentence Level (Sentence Level):

With this method, positive, negative or neutral conclusions are made on a sentence basis. Neutral generally means that there is a sentence that does not express feelings or ideas.

Many objective sentences may contain thoughts, but not subjective thoughts, and this situation should be explained with a small example.

Entity and Aspect Level:

Document-level and sentence-level analyzes cannot discover exactly what people love and dislike. Whereas the Level of Existence and Opinion enables to perform small-grain analysis, it provides more accurate analysis.

Aspect Level was previously known as Feature Level. With this method of analysis, he deals directly with emotion rather than looking at language structures. In this case, Document and sentence level makes it different from analysis.

For example: “I still love this restaurant, although its service is not perfect.” Although the sentence has a positive tone, we cannot say that it is completely positive. Although there is a positive opinion about the restaurant, it contains a negative opinion.
Labels:

Comments

Post a Comment

Popular posts from this blog

Coronavirus Begins To Disturb Chinese Technological Production

Coronavirus Begins To Disturb Chinese Technological Production The coronavirus outbreak in China is beginning to affect the global technology industry, with noticeable declines in shipments of devices such as graphics cards and mobile phones. Asus, Foxconn and Gigabyte  have said that first-quarter shipments of motherboards and graphics cards have fallen more than expected, British media outlet Computing has reported . This decline is explained by the fact that Chinese people avoid public places and shops, while courier delivery and other services have been affected. Meanwhile, the smartphone market is expected to be affected in two ways: first, with excess inventory in China caused by the sudden and unexpected decline in sales, and second, the halt of new models due to the pause. in supply chains, caused by factory closings, ordered by the Chinese government when the epidemic began. Huawei, in particular, is likely to be hit hard as it fell back on its home market due t...
Post a Comment
Read more

Big Data

Data collection and interpretation are very important to the seed breeding program. Without data and its interpretation, progress is impossible. Technology will create the ability to collect new data, and the effective innovation of a successful company will result. In addition, as technology evolves, the cost of technology decreases. For example, the cost per gigabyte of storage in 1980 was $ 500,000. Today the price is less than $ 0.03. This is a huge expense for the amount of data collected. In pig breeds, there is a wave of data collection. Basic data collection includes weight, number of births, birth year, age group, wean to service time, door count, and more. These features do not require sophisticated technology. Ultrasonic balance, depth, and intramuscular oil are being collected because of advances in ultrasound technology. Improvements in body and food quality have emerged over the years, including tools to improve pH, maripling, color, and digestion. All of these factors ar...
Post a Comment
Read more

Internet simply explained

Internet simply explained  The Internet is a worldwide network of several million computers. The computers that essentially provide services to other systems are referred to as servers. The servers are connected via Internet service providers (ISP), who manage (host) the information as Internet pages (websites, blogs, shops, email accounts etc.) and make them available to visitors (users). You can use the Internet to query information from all of these computers, send electronic messages to recipients around the world, shop around the clock, book trips, and much more. Internet history The Internet (from the English internetwork, composed of the prefix inter and network 'network' or 'net' for short) is a worldwide network of computers. It combines Internet services such as WWW, email, Telnet, Usenet and FTP. Any computer can connect to any other computer, provided you know its address. Colloquially, the Internet is also used instead of the Internet. The data exch...
Post a Comment
Read more