“Personalization,” which is the tailoring of a product to the specific interests and needs of an individual, has been widely heralded as an important web innovation as search engines, and websites in general, work to deliver greater value to users. There are, in general, two types of personalization, explicit and implicit, which must both be employed to achieve the greatest benefit for the user. Through the examination of some of the limitations of the former, however, we can gain a greater appreciation for the importance of the latter.

• Explicit personalization, also referred to as “customization,” is the process through which users shape their experiences by actively selecting preferences or responding to questions. Within search, voting for, rating or deleting particular results, or any adjustment on a ‘Preferences’ or ‘Options’ page, are obvious examples of explicit personalization. Less obvious, however, are things such as presenting suggested search terms or similar queries to the user, such as with Yahoo! Search Assist or Google Suggest. Clustering (the process of suggesting possible query reformulations through the analysis of similarities between documents in the result set) is also a form of explicit personalization. In all of these cases the onus is upon to user to make a determination as to the path forward and then actively select an option.

• Implicit personalization is the process through which the users’ experiences are shaped by inferences of intent generated through the careful observation of behavior. Google’s Personalized Search, which delivers a modified set of results based on past search activity, is a clear example. Leveraging behavioral analysis or social relationships to target anything from advertising to search results to any other sort of content is also implicit personalization.

One is not better than the other. They are simply different and, to a great extent, compatible. Explicit personalization by itself, however, suffers from a number of limitations that can be alleviated through the addition of implicit personalization:

1. Explicit personalization, by definition, requires effort on the part of the user and many people merely will not bother. It seems that users want to enter their queries and then simply go straight to the results, scanning from top to bottom.
2. Even if users are willing to make the effort, they don’t necessarily know with enough precision what it is that they want. Furthermore, in some cases they might not yet possess enough knowledge to comprehend the clusters or suggestions. While clusters may sometimes help with reformulation, since it is often easier to recognize terms rather than recall them, search is frequently a process of discovery, with each result leading to better understanding of the subject matter and a greater ability to express intent. Knowing all of this a priori is not always possible.
3. Explicit personalization through a classification or clustering of search results may also create additional work if the user’s intent spans multiple contexts or sub-contexts. Selecting a cluster, for example, will enable the user to ‘zoom in’ on a particular sub-context. However, if the sub-context is not a precise match, or if the nature of the search requires a body of information that covers multiple sub-contexts, then the user will have to expend additional effort going up and down the classification tree.
4. Even if users think they know what they want, they still might be mistaken. Or worse, either intentionally or not, they are not always honest with themselves. Based on the ability to observe user behavior on all of Yahoo!’s properties, Dr. Usama Fayyad stated, “I know more about your intent than any 1000 keywords you could type,” which of course alludes to the difficulty of both accurately knowing and then expressing one’s own intent.

It is for these reasons that implicit personalization is an important compliment to explicit personalization. One could compare it to the focus adjustments of a telescope, with the course adjustment being explicit personalization and the fine adjustment being implicit personalization; you could certainly make out some celestial objects with only the course adjustment, but you need the fine adjustment to really discern the details.