Financial Text Mining: Supporting Decision Making Using Web 2.0 Content

Deep penetration of personal computers, data communication networks, and the Internet has created a massive platform for data collection, dissemination, storage, and retrieval. Everyday, people engage in numerous online activities, including reading the news and product reviews, commenting on developing events, buying and selling stocks, and widening their social networks. This widespread engagement with online worlds has facilitated the creation of large amounts of textual data. For financial institutions, keeping track of important events and sentiments in a near real-time fashion could accelerate their decision-making process. With the help of text-mining techniques (the “fishing poles”), tangible profits can arise from smart trading strategies and improved portfolio management. Making sense of the continual stream of textual data requires the development of a surveillance system that can collect, filter, extract, quantify, and analyze relevant information from the Internet. The nature of textual data, however, presents unique challenges. Although researchers and practitioners have achieved a certain level of success in extracting factual information, comprehending the meaning and implication of financial documents and investment strategies from a large collection of Web-based textual data is far more difficult. Types of Finance-Related Textual Conten