searchnuggets
Hunch!
Hunch is a new website (in private beta) that helps you make decisions faster, and perhaps even better. Questions like "What should I be for Halloween? Do I need a Porsche? What toe ring should I buy?" are broken down into a series of sub-questions, guiding you quickly through to the final conclusion. Decision-making is difficult, and decisions have to be made constantly. This is where I believe recommendation systems still have a way to go, for them to become efficient decision facilitators, and not merely option generators. Perhaps Hunch is the next step in that direction? I'm still waiting for my invite, and as soon as I get my hands on one, I'll let you know if my hunch is right.
Hunch!
Hunch is a new website (in private beta) that helps you make decisions faster, and perhaps even better. Questions like “What should I be for Halloween? Do I need a Porsche? What toe ring should I buy?” are broken down into a series of sub-questions, guiding you quickly through to the final conclusion. Decision-making is difficult, and decisions have to be made constantly. This is where I believe recommendation systems still have a way to go, for them to become efficient decision facilitators, and not merely option generators. Perhaps Hunch is the next step in that direction? I’m still waiting for my invite, and as soon as I get my hands on one, I’ll let you know if my hunch is right.
Google’s Wonder Wheel Experiment
Want to participate in one of Google's user interface experiments? Google Blogoscoped tells you how to grant yourself access to the Google Wonder Wheel. Go to google.com, paste the Javascript into the address bar, and take the wonder wheel for a spin. The wheel displays a circle with your keyword, connected to other circles with related terms. There's also a timeline view, and options to show longer snippets and more images for each search result. You can also use filter the results on type (recent, videos, forums and reviews), as well as freshness (time and date). The related terms aren't based on Google's Latent Semantic Analysis (LSI), which you can access by prefixing your keyword with the tilda (~) operator. Google then expands you search with semantically (actually derived from statistics) related concepts. I wonder why they decided not to fuse the two related terms initiatives. (via http://thenoisychannel.com)
Google’s Wonder Wheel Experiment
Want to participate in one of Google’s user interface experiments? Google Blogoscoped tells you how to grant yourself access to the Google Wonder Wheel. Go to google.com, paste the Javascript into the address bar, and take the wonder wheel for a spin. The wheel displays a circle with your keyword, connected to other circles with related terms. There’s also a timeline view, and options to show longer snippets and more images for each search result. You can also use filter the results on type (recent, videos, forums and reviews), as well as freshness (time and date). The related terms aren’t based on Google’s Latent Semantic Analysis (LSI), which you can access by prefixing your keyword with the tilda (~) operator. Google then expands you search with semantically (actually derived from statistics) related concepts. I wonder why they decided not to fuse the two related terms initiatives. (via http://thenoisychannel.com)
Four Approaches to Music Recommendations: Pandora, Mufin, Lala, and eMusic
ReadWriteWeb gives us some nice examples of the kinds of recommendation systems I wrote about in my previous post. Pandora is content-based, although the features are extracted by humans. The result is high-quality data, but poor scalability. Mufin is a classical example of content-based music recommenders, using a purely algorithmic approach. Lala seems to be old-fashioned word-of-mouth recommendations put on the Internet. eMusic is a hybrid system, but combines social with expert, and social with content-based like Oscar Celma proposes. Apple Genius is most likely a typical collaborative filtering recommender, based on artist (not song or album) similarity.
Four Approaches to Music Recommendations: Pandora, Mufin, Lala, and eMusic
ReadWriteWeb gives us some nice examples of the kinds of recommendation systems I wrote about in my previous post. Pandora is content-based, although the features are extracted by humans. The result is high-quality data, but poor scalability. Mufin is a classical example of content-based music recommenders, using a purely algorithmic approach. Lala seems to be old-fashioned word-of-mouth recommendations put on the Internet. eMusic is a hybrid system, but combines social with expert, and social with content-based like Oscar Celma proposes. Apple Genius is most likely a typical collaborative filtering recommender, based on artist (not song or album) similarity.
All hail the information triumvirate!
Wikipedia has come to dominate Google web search results. It often ranks #1 for searches on common topics like Internet and Evolution. Is it true that Wikipedia articles are the very best source of information for all of these topics? Or are we witnessing the effects of a popularity feedback loop, fueled by the principles of least effort, and our tendency to stick with the first and obvious answers? The web link graph is fundamentally a product of socialization, and Google is fundamentally a social search engine. A popularity bias in inherent in all social information systems, leading us all down the same well-trod path. Could it be that, counter to our expectations, the natural dynamic of the web will lead to less diversity in information sources rather than more?
All hail the information triumvirate!
Wikipedia has come to dominate Google web search results. It often ranks #1 for searches on common topics like Internet and Evolution. Is it true that Wikipedia articles are the very best source of information for all of these topics? Or are we witnessing the effects of a popularity feedback loop, fueled by the principles of least effort, and our tendency to stick with the first and obvious answers? The web link graph is fundamentally a product of socialization, and Google is fundamentally a social search engine. A popularity bias in inherent in all social information systems, leading us all down the same well-trod path. Could it be that, counter to our expectations, the natural dynamic of the web will lead to less diversity in information sources rather than more?
Search Inside Obama’s Inaugural Speech
Delve Networks has applied its audio search technology to Obama's inagural speech. When you enter keywords into the search field below the video, those words are highlighted on the timeline, guiding you to the most relevant parts of the video. Audio search is difficult to execute properly, since human speech is imprecise and varies wildly from person to person. Delve Networks have done a good job, however. I'll take a close look at various audio search engines in a future blog post.
Search Inside Obama’s Inaugural Speech
Delve Networks has applied its audio search technology to Obama’s inagural speech. When you enter keywords into the search field below the video, those words are highlighted on the timeline, guiding you to the most relevant parts of the video. Audio search is difficult to execute properly, since human speech is imprecise and varies wildly from person to person. Delve Networks have done a good job, however. I’ll take a close look at various audio search engines in a future blog post.
Latest Comments