Our goal is to present how we use the “huge data” collected by using open APIs of Twitter and other online services to empirically test and improve existing models in social sciences such as economics and sociology. Bringing together natural language processing and macroeconomics, on top of the troves of machine-generated data, we also propose building innovative applications to track consumer sentiment and industry dynamics.
by Liangfei Qiu
Information aggregation mechanisms are designed explicitly for collecting and aggregating dispersed information. A best example of utilizing such kind of "the wisdom of crowds" is prediction market. The purpose of our project is to suggest that carefully designed market mechanisms can elicit dispersed information, which will improve our prediction. In a prediction market, payoffs are tied to the outcomes of future events and one typically trades a security that pays $1 if a specified event occurs. Generally speaking, participants are compensated for accuracy in forecasting. Many business examples share the following characteristic: small bits and pieces of relevant information exists in the opinions and intuition of diverse individuals. The prediction markets will produce reliable forecasts about sales, financial and accounting results by gathering small pieces of individual information. The development of the Internet provides us with a twitter based technology to design prediction markets. The information propagation in twitter community is a complex social network, and will improve people's predictions in prediction markets.
11th–15th March 2011