Guest Author Nitin Karandikar over at Read/Write Web has published a list of the top 17 search innovations taking place outside of Google. As you might imagine, a few of them caught our eye, so I thought I would walk through the various innovations that we’re working on here at mySidekick.
8. Social Input
Yahoo!’s Bradley Horowitz believes social input to be a big differentiator of search technologies in the future (as does Microsoft). Aggregating inputs from a large number of users enables the search engine to benefit from the wisdom of crowds and provide high quality search results. Of course, the results may not be valid if the individual inputs are not independent or can be gamed.
Utilizing Social Input is at the core of the mySidekick system. As our Beta testers know, the mySidekick system allows the searcher to see the best results for what other people have already found about your topic across many related search requests.
Here’s how we do it: When you search for stuff online, you might change your search request a few times before you finally find what you are looking for. In fact, if you’re like the rest of us, you’ll change your search request about three to four times during an average search. MySidekick groups these search requests together as a set of “tags” that describe the topic you and other people have researched.
We then use our own relevancy algorithms to figure out exactly which sites people liked for those tags, and promote those sites as the “People’s Choice” for other mySidekick community members. When other people search for a similar topic, these tags help them more easily find what they are looking for in the People Choice’s area. The end result is better search results for everyone.
Of course, like all socially driven sites, we have to be on the lookout for gaming and have built a number of defenses against result manipulation, most of which rely on a diverse set of users and require meaningful traffic to work best.
9. Human Input
This approach is included in the list for completeness. Search engines like ChaCha are experimenting with using human operators to respond to search queries. Arguably, Yahoo! Answers is another solution in this space, although the answers are provided by other users rather than by people working for the search engine.
MySidekick also allows searchers to suggest a site that would be useful for a particular search request. If other people think the suggested site is relevant to their topic, then the site will be placed higher in the results for requests related to the suggested tags and the tags that other people find relevant to the site.
In other words, sites submitted into the mySidekick system are also forced to compete with organic search results and will either rise of fall based on their performance with real users across multiple aggregrated queries and tag sets.
14. Results refinement and Filters
Often a natural next step after a search is to drill down into the results, by further refining the search. This is different from the “keyword-tweaking” that we’ve all gotten used to with Google; it’s not just experimenting with keyword combinations to submit a new query, but rather, an attempt to actually refine the results set [akin to adding more conditions to the “where” clause of a SQL query] - this would allow users to narrow the results and converge on their desired solution.
MySidekick also automatically incorporates an interesting twist on query refinement. Basically, mySidekick automatically aggregates all of the query refinements made by searchers when they refine their various search requests during a search session.
We then analyze and use this aggregated data showing the relationships across multiple queries and between various queries and their results to cross-pollinate various search results across search requests and tag sets. If that sounds a bit complicated, it’s because it is a bit tricky to track all of this data and make sure it is properly used to provide better results for all.