Social Media Research Blog

Youlicit: Search Less and Find More!

Youlicit is a new tool that helps you "Search less and find more". Often we forget that search is only one means to find what we are looking for. Even search by itself is not the endpoint of an information need or a query. This tool reminds me of the "berry picking model" of Information Retrieval that I had read about first in my IR Class. The model basically says that:

Information need is not satisfied by a single set of documents but by bits and pieces found along the way.

The paper  titled "The Design of Browsing and Berrypciking Technique for Online Search Interface" describes a searcher as

Moving through many actions towards a general goal of satisfactory completion of research related to an information need.

What Youlicit does is provide this ability implicitly, without the reader (or more generally a searcher) having to go through the trouble of navigating and mentally processing through hyperlinks or firing search queries to find related content. Youlicit takes care of all that on your behalf. By providing a simple plugin, the Youlicit widget automatically highlights some of the related, relevant links and provides useful suggestions -- all without your audience ever leaving your blog. I love the idea and the neat implementation that these guys have built. (The very same need was what lead me to hack this Wikipedia related widget a few weeks earlier.)

On the Youlicit site, you have lots more interesting tools. You can discover new content that is relevant to your interests, find related users and share links with them or follow their interests. Youlicit is paving the way for social browsing tools and is a neat concept that is well implemented. Their index does not seem to be very large at the moment and I feel that it would get better as they start to seriously scale up. In the interim, I feel that there might be stopgap solutions that they could be employ -- for example the Alexa related URLs for the links that are not currently in Youlicit's index.

In relation to this plugin, one tool that is similar is the  Sphere plugin that shows related blog posts. I feel that sphere serves a complementary need. From what I understand Youlicit aims to find the interesting blogs and Web URLs one might want to look into in relation to a given hyperlink.

Another plugin is the Snap plugin -- which shows a screenshot of the outlink. However, in my opinion snap does not really serve much purpose and is a bad tool from a usability perspective.

Youlicit is non-intrusive and you are gonna enjoy the serendipity of finding interesting new links! Give it a spin!

Leaveraging Web and Social Media for Recommendations

Both Amazon and Netflix's business models rely on effective recommendation systems. The recommendations provided by such systems are based on the purchasing habits of millions of customers. As such, these systems are non-trivial and have evolved out of years of research in both academia and industry.

In addition to mining millions of customer transaction records, for many products there is a vast amount of information available online. While I do not have a lot of familiarity with recommendation systems literature, it seems obvious that the Web and Social Media is a great source of information that could be useful when building such systems.  Bloggers' profile pages, wishlists, netflix queues, book lists and the blog posts themselves are potential clues to learn which two items may be related to each other.

As a simple example, consider the movie "Pulp Fiction", by querying Google for all the inlinks to the IMDB homepage of Sin City Pulp Fiction and counting which are the other movies that are "co-cited" here is a list of five movies that are most likely to be related to "Pulp Fiction":

Most of these look quite relevant. Some critics have claimed similarities between Pulp Fiction and Snatch. One surprise though was LOTR, I wouldn't have expected it to be grouped with Pulp Fiction, but I guess I like them both very much -- so it seems reasonable in my case atleast.

Just for fun, here is another example with "Sin City" another one of my favorite movies.

Unless you have a large index of the Blogosphere or the Web, it would be quite inefficient to mine for such correlations (by passing queries to search engines) on a large scale. I do not know how much of the search engine information is leveraged in recommendation systems built by Amazon or Netflix.  It might also be worth looking into differences in the recommendations produced on the basis of "how people co-cite two products" vs. "how people purchase two products".