Understanding Temporal Query Dynamics Anagha Kulkarni Jaime Teevan, Krysta M. Svore, Su san T. Dumais Carnegie Mellon University Microsoft Research Pittsburgh, PA, USA Redmond, WA, USA
[email protected] {teevan, ksvore, sdumais}@microsoft.com time game information, became relevant to people seeking to learn the ABSTRACT score of a game in progress. In contrast, relatively static pages, like Web search is strongly influenced by time. The queries people issue the Wikipedia page about March Madness, became less relevant change over time, with some queries occasionally spiking in during this period of high interest. Such pages are useful for learning popularity (e.g., earthquake ) and others remaining relatively constant about March Madness in general, but not for actively monitoring the (e.g., youtube ). Likewise, the documents indexed by a search engine event, and thus are better suited to satisfy the need of searchers when change, with some documents always being about a particular query the query is not spiking. The changes in which pages were relevant to (e.g., the Wikipedia page on earthquakes is about the query the query march madness during the month of March reflects the fact earthquake ) and others being about the query only at a particular point that people’s query intent was also changing. in time (e.g., the New York Times is only about earthquakes following a major seismic activity). The relationship between Understanding changes to query popularity, Web content, query documents and queries can also change as people’s intent changes intent, and relevance is fundamental to understanding the search (e.g., people sought different content for the query earthquake before experience.