The paper presents the result of experiments that were designed with the goal of revealing the association between texts published in online environments (Yahoo! Finance, Facebook, and Twitter) and changes in stock prices of the corresponding companies at a micro level. The association between lexicon detected sentiment and stock price movements was not confirmed. It was, however, possible to reveal and quantify such association with the application of machine learning-based classification. From the experiments it was obvious that the data preparation procedure had a substantial impact on the results. Thus, different stock price smoothing, lags between the release of documents and related stock price changes, five levels of a minimal stock price change, three different weighting schemes for structured document representation, and six classifiers were studied. It has been shown that at least part of the movement of stock prices is associated with the textual content if a proper combination of processing parameters is selected.

The goal of the article was to examine the relationship between the content of text documents published on the Internet and the direction of movement of stock prices on the Prague Stock Exchange. The relationship was modeled by text classification. As data were used news articles and discussion posts on Czech websites and the value of the PX stock index and stock price of company CEZ. Document's class (plus/minus/constant) was determined by the relative price change that happened between the publication date of a document and the next working day. We achieved a high accuracy of 75% for classification of discussion posts, however the classification accuracy for news articles was about 60%. We tried both binary (documents with constant class were discarded) and ternary classification -the former was in all cases more successful.

A lot of research has been focusing on incorporating online data into models of various phenomena. The chapter focuses on one specific problem coming from the domain of capital markets where the information contained in online environments is quite topical. The presented experiments were designed to reveal the association between online texts (from Yahoo! Finance, Facebook, and Twitter) and changes in stock prices of the corresponding companies. As the method for quantifying the association, machine learning-based classification was chosen. The experiments showed that the data preparation procedure had a substantial impact on the results. Thus, different stock price smoothing, the lags between the release of documents and related stock price changes, levels of a minimal stock price change, different weighting schemes for structured document representation, and classifiers were studied. The chapter also shows how to use currently available open source technologies to implement a system for accomplishing the task.

Each day, a lot of text data is generated. This data comes from various sources and may contain valuable information. In this article, we use text mining methods to discover if there is a connection between news articles and changes of the S&P 500 stock index. The index values and documents were divided into time windows according to the direction of the index value changes. We achieved a classification accuracy of 65–74 %.

A lot of research has been focusing on incorporating online data into models of various phenomena. The chapter focuses on one specific problem coming from the domain of capital markets where the information contained in online environments is quite topical. The presented experiments were designed to reveal the association between online texts (from Yahoo! Finance, Facebook, and Twitter) and changes in stock prices of the corresponding companies. As the method for quantifying the association, machine learning-based classification was chosen. The experiments showed that the data preparation procedure had a substantial impact on the results. Thus, different stock price smoothing, the lags between the release of documents and related stock price changes, levels of a minimal stock price change, different weighting schemes for structured document representation, and classifiers were studied. The chapter also shows how to use currently available open source technologies to implement a system for accomplishing the task.