Grant: Engage Plus Grants Program

Twitter and other public social micro-blogging services have become valuable sources of information regarding the public opinion of various products, services, and events. Some researchers have explored methods for extracting positive/neutral/negative sentiment from such information and correlating this against market performance, lending credence to the idea that public opinion expressed via Twitter can be used as a surrogate for consumer or investor research. While such work illustrates the potential for mining sentiment from Twitter and using this as an indicator for market performance, the approaches have yet to be shown to be useful for investment analysts.The goal of this research is to build upon our prior work in using Vista (Visual Twitter Analytics) to support investment analysis tasks. With the support of an NSERC Engage Grant (Oct 2013 - Mar 2014), the preliminary proof-of-concept approach for visually analyzing the temporally changing sentiment on Twitter developed in prior work was enhanced with respect to the project infrastructure, sentiment classification processes, and the visual interface for exploring among the data. Building upon the success of this project, the goal for this Engage Plus Grant will be to further enhance and refine Vista in two regards: (1) developing robust anomaly detection algorithms that can alert investors to noteworthy changes in public sentiment expressed in Twitter, which can be further explored in Vista; and (2) refining the visual interface of Vista to further improve its usefulness and efficiency for the exploration and analysis of the Twitter data.