Christine Robson

Midas: integrating public financial data

The primary goal of the Midas project is to build a system that enables easy and scalable integration of unstructured and semi-structured information present across multiple data sources. As a first step in this direction, we have built a system that extracts and integrates information from regulatory filings submitted to the U.S. Securities and Exchange Commission (SEC) and the Federal Deposit Insurance Corporation (FDIC). Midas creates a repository of entities, events, and relationships by extracting, conceptualizing, integrating, and aggregating data from unstructured and semi-structured documents. This repository enables applications to use the extracted and integrated data in a variety of ways including mashups with other public data and complex risk analysis.

Multimodal social intelligence in a real-time dashboard system

Social Networks provide one of the most rapidly evolving data sets in existence today. Traditional Business Intelligence applications struggle to take advantage of such data sets in a timely manner. The BBC SoundIndex, developed by the authors and others, enabled real-time analytics of music popularity using data from a variety of Social Networks. We present this system as a grounding example of how to overcome the challenges of working with this data from social networks. We discuss a variety of technologies to implement near real-time data analytics to transform Social Intelligence into Business Intelligence and evaluate their effectiveness in the music domain. The SoundIndex project helped to highlight a number of key research areas, including named entity recognition and sentiment analysis in Informal English. It also drew attention to the importance of metadata aggregation in multimodal environments. We explored challenges such as drawing data from a wide set of sources spanning a myriad of modalities, developing adjudication techniques to harmonize inputs, and performing deep analytics on extremely challenging Informal English snippets. Ultimately, we seek to provide guidance on developing applications in a variety of domains that allow an analyst to rapidly grasp the evolution in the social landscape, and show how to validate such a system for a real-world application.

Data collection by the people, for the people

Data Collection by the People, for the People is a CHI 2011 workshop to explore data from the crowd, bringing together mobile crowdsourcing & participatory urbanism researchers with data analysis and visualization researchers. The workshop is two-day event beginning with day of field work in the city of Vancouver, trying out mobile crowdsourcing applications and data analysis tools. Participants are encouraged to contribute applications and tools which they wish to share. Our goal is to provoke discussion and brainstorming, enabling both data collection researchers and data manipulationanalysis researchers to benefit from mutually learned lessons about crowdsourced data.

Information Enrichment Service Systems

Information enrichment is generally considered a modern task of supplying specific-necessity metadata to an existing body of information, with the intent to enable a particular task. In this paper we suggest that information enrichment service systems have been existent for thousands of years, and that information has often been enriched in more generically useful ways than just for a single task. Viewing information enrichment as a service system provides a framework for thinking about how to better implement and leverage the wealth of knowledge in modern organizations.