My friends at Summize have been doing some really interesting things. Their first demo, now offline, was a new twist on product search. They spidered for reviews from various sources and performed sentiment analysis to unify ratings and reviews. I was particularly fond of their use of stacked bar histograms to efficiently summarize people’s sentiments. Display such as these convey much more distributional information than simply reporting averages.
Currently, Summize’s showcase product is a Twitter search application. Their search application is nice because you can get real-time updates of matches as the tweets are happening. Twitter’s recognized the value of Summize’s conversational search, and linked to Summize for live coverage of WWDC. I think it’s great when small companies collaborate in these ways. It’s also a smart move for Twitter today, given the troubles they’ve been having recently. Diverting some of their traffic to Summize might help them handle today’s load.
Looking at the results of Twitter’s suggested search, I feel a little overwhelmed. Just a few seconds after clicking on the link, Summize’s search results informed me that there have been an additional 26 posts matching the search since the page was loaded. Letting the page go for a minute without refreshing showed hundreds of new tweets. That’s not terribly surprising, given the excitement around WWDC. But here’s the rub. Most of these tweets are useless to me or contain redundant information. I want only the unique information, not the chatter. For high volume topics of discussion, I really need the conversational search to filter or summarize the results for me. Abdur and Eric, please bring some of the great summarization and organizational aspects of your product search to your conversational search.