Attitudes and opinions expressed in social networks, online forums and blogs are referred to every day to support countless investment decisions. Information on sentiment enables early identification and evaluation of events that have an impact on the financial markets. However, the difficulty is in collecting the unstructured content from the Internet and sorting and analysing it quickly. Suitable software is needed in order to enable financial market participants to use the data directly to support their decision processes. The development of such solutions was the focus of the EU research project FIRST, which has now been successfully completed after three years of work.
The findings of the FIRST project show how the sentiment reflected in individual English-language Internet postings can be automatically analysed and summarised to form an indicator. This source of information increases the probability that financial market trends can be correctly anticipated. Christoph Lammersdorf, CEO of the Management Board of Boerse Stuttgart Holding GmbH, commented: “Such tools could also help private investors making investment decisions to factor in social media content more efficiently. As an exchange organisation for the retail business, we see it as our job to support research into innovative technologies for private investors.”
Ulli Spankowski, who led the project for Boerse Stuttgart and Stuttgart Financial, highlighted another area of application: “The software developed for the FIRST project also enables early detection of manipulative behaviour on the part of individual market participants. That opens up new opportunities for trading surveillance offices and other regulatory authorities.” The targeted use of heuristics created with market surveillance experts makes certain instances of manipulation on the Internet easier to identify. Manipulation could involve the deliberate posting of false information on social media, for instance in ‘pump and dump’ schemes. The operators of such schemes attempt to inflate the price of a share by publishing a large amount of very positive information and then sell their holdings at a profit before the deception comes to light.