This is the first of a three part series on how the Darwin Awareness Engine™ addresses some of the key problems generated by information overload on the Web. The Awareness Engine is a Web aggregation utility for anyone needing to maintain awareness of emerging events from the Internet and intranet. The technology provides a temporal semantic visualization of events, by means of a Scan Cloud™ that facilitates a rapid understanding of trends, outliers and anomalies.
Issue One: Too many sources, too many events.
As an information aggregator we target theme-specific sources through search and specific feeds. Although accessible from on site edition, this body of information often remains overwhelming. In contrast with traditional search engines, we do not first deliver the events in lists. Instead, these are presented in a Scan Cloud, revealing both the relative importance of terms as well as their inter-relation. This interactive representation makes it easier to understand the content without having to read through the content of the articles to understand “what is going on” and detecting emerging themes. The user’s natural ability to infer meaning is leveraged by the tool.
Example: During a presentation of Darwin Awareness Engine to a large energy holding company, the information curator, responsible for providing the CEO with reports on all public, political, and news events related to the company’s business and its owner’s public image, spotted the term “London” in the ScanCloud. Most other terms and their highlighted relationships where within the expected context, but “London” was an anomaly (only someone with an intimate understanding of the company’s activities would have made this assessment).
She asked to be excused for 5 minutes and returned to the meeting. She shared with us that despite the tools currently available to her to comb the Web and the press, she had not noticed the event she just discovered using the Awareness Engine. In fact, the event related to the violation of a UK court gag order that could have caused material damage to the company. She identified the blogger and reported it to the Legal department. Subsequently she added the event to the CEO’s daily report.
In the next post I will look at popularity versus temporal correlation ranking as a means to uncover relevant content.
Comments