Inferring Searcher Attention and Intention by Mining Behavior Data

19/03/2015 - 12:00

A long standing challenge in Web search is how to accurately determine
the intention behind a searcher’s query, which is needed to rank,
organize, and present information most effectively. The difficulty is
that users often do not (or cannot) provide sufficient information
about their search goals.  As this talk with show, it is nevertheless
possible to read their intentions through clues revealed by behavior,
such as the amount of attention paid to a document or a text fragment.
I will overview the approaches that have emerged for acquiring and
mining behavioral data for inferring search intent, ranging from
contextualizing query interpretation and suggestion, to modeling
fine-grained user interactions such as mouse cursor movements in the
searcher’s browser. The latter can also be used to measure the
searcher’s attention “in the wild’’, with granularity approaching that
of using eye tracking equipment in the laboratory. The resulting
techniques and models have already shown noteworthy improvements for
search tasks such as ranking, relevance estimation, and result summary
generation, and have applications to other domains, such as
psychology, neurology, and online education.

Eugene is a Principal Research Scientist at Yahoo Labs in Haifa, on
leave from Emory University, where he is an Associate Professor and
founder of the IR Laboratory. Eugene's research spans the areas of
information retrieval, data mining, and human computer interaction. At
Yahoo Labs, he works on the Answering Research team trying to
automatically answer questions from millions of searchers. Dr.
Agichtein is actively involved in the international research
community, having co-authored over 100 publications (including 4 best
paper awards), co-chaired the ACM WSDM 2012 conference (with Yoelle
Maarek), and served on the program or organizing committees of all the
main information-retrieval and web search conferences.