Research Paper: "Information Seeking: Convergence of Search, Recommendations and Advertising"

All of us are faced with a “deluge of data” [2], in our work- places and our homes: an ever-growing World Wide Web, digital books and magazines, photographs, blogs, tweets, e- mails, databases, activity logs, sensor streams, on-line videos, movies and music, and so on. Thus, one of the fundamen- tal problems in Computer Science has become even more critical today: how to identify objects satisfying a user’s information need. The goal is to present to the user only information that is of interest and relevance, at the right place and time.

At least three types of information providing mechanisms have been developed over the years to satisfy user informa- tion needs:

• A search mechanism takes as input a query that de- scribes the current user interests. A body of objects (e.g., documents, records) is searched, and ones that somehow match the query are returned. For example, in a Web search engine, a user may enter a sequence of words (the query), and is given a ranked list of Web pages that contain the desired words. In a database system, the query is typically more structured (e.g., I want the names of products with price less than 100 dollars) and the search is over structured records.
• A recommendation mechanism typically does not use an explicit query but rather analyzes the user context (e.g., what the user has recently purchased or read), and if available, a user profile (e.g., the user likes mys- tery novels). Then the recommendation mechanism presents to the user one or more descriptions of objects (e.g., books, people, movies) that may be of interest. For example, in an electronic commerce site, when a user purchases one object, he may be shown a set of similar objects, or objects that other people have pur- chased together with the just purchased object. In a Web search engine, when a user types in one query, he may be shown a list of related queries that others have entered following the first query.