A lot of financial traders prefer to pay a lot for newswire services such as Bloomberg, Thomson Reuters, and Matriks in order to instantly be aware of news related economic events and stock markets. These services help the invertors to make better decisions faster. Because they provide usually publicly-available information about financial, legal, risk management, tax & accounting, government, technology, scientific, new and media with presenting very specialized information tools.
In recent years, social media have become a new hybrid component of integrated marketing communications (IMC) that allow organizations to establish strong relationships with their consumers.
Peterson (2007) searched the relationship with perspective of neuroscience works the effect of emotions, moods, and approaches on making a financial decision. He stated brain systems and its effect of trading attitudes. His paper aimed to teach investors about avoiding that their emotions cause to make unfavorable financial decisions. He suggested that over excessive pressure and motivation play a major role our investment decision and preference of our trading attitudes.
Leinweber and Sisk (2011) emphasized that new analyses to predict the future focus on computer linguistic analyze rather than market information based on quantitative valuable. Twitter has become a vibrant platform to exchange trading ideas and other stock-related information. Da et al., (2011) find a correlation between Search Volume Index in Google and stocks of 3000 companies in Russell for 4 years periods. They were the first articles with Mondria et al. (2010) to utilize internet search volume index for sentiment analysis (Da, et al., 2011). They resulted that rising in Google Search Volume index can be a useful tool to forecast higher price in the stock markets in the following two weeks. In recent years, with the significant increase and popularity of mobile marketing, Sven (2013) tried to defined “sentiment” term. Because, the literature is usually interested in the effect of sentiment analyze on stock markets. The author displays a basic definition for sentiment. Therefore, they aim to study the sentiment indexes really measure sentiment or another different something. Primarily, Sven used 2 factor analyses and he divided sentiment as emotion and mood. Emotion represents short term sentiment; on the other hand, mood represents long term sentiment. As a result, he provided validated and stable result for different time sentiment analysis. Gu et al. (2014) used electroencephalography of the brain for sentiment analysis. They created a sentiment valence map with this electroencephalography signals. They predicted the valence of 12 sentences using the lexical polarity which come from brain data. With this paper, they confirmed that analysis based on electroencephalography signal provided a better performance that the analysis based on machine learning techniques such as Naive Bayes Classification or Support Vector Machines.
Machine learning or in other words artificial intelligence is a system which is mostly based on computer programs and they have ability learning and improving themselves automatically without any intervention. With developing high-technology, these programs are begun to use in financial world. Researcher discovered that these systems can be convenient to imply linguistic analysis. Because scholars supposed that if some values inserted to digital systems according to the some predefined rules, they can be useful tools for financial predictions. With this line, one of using field of machine learning system became computational linguistic analysis. Machine learning system defined as automatically receiving the news, categorizing them, and implying sentiment analysis. Nowadays, not only individual investors or scholars but also huge hedge funds began to use these machines and its algorithms for prediction stock market. iSentium LLC is one technology company which analyses one million tweets daily to define sentiment analyses for stock companies. ISentium said that some of their clients are huge amount of hedge funds use based on computational algorithmic sentiment analysis models to forecast stock movements. (Hope & Huang, 2015).