Hapori: Context-based Local Search for Mobile Phones
using Community Behavioral Modeling and Similarity
Nicholas D. Lane, Dimitrios Lymberopoulos
, Feng Zhao
and Andrew T. Campbell
Dartmouth College, Microsoft Research
Local search engines are very popular but limited. We present
, a next-generation local search technology for mo-
bile phones that not only takes into account location in the
search query but richer context such as the time, weather and
the activity of the user. Hapori also builds behavioral mod-
els of users and exploits the similarity between users to tai-
lor search results to personal tastes rather than provide static
geo-driven points of interest. We discuss the design, im-
plementation and evaluation of the Hapori framework which
combines data mining, information preserving embedding
and distance metric learning to address the challenge of cre-
cient multidimensional models from context-rich
local search logs. Our experimental results using 80,000
queries extracted from search logs show that contextual and
behavioral similarity information can improve the relevance
of local search results by up to ten times when compared
to the results currently provided by commercially available
search engine technology.
Local Search, Context-ware Mobile Search, Mobile Phone
H.4.m Information Systems Application: Miscellaneous.
Design, Experimentation, Performance.
Location-based services on mobile phones have been stan-
dard fare for several years. People on-the-go regularly use a
variety of mobile local search applications throughout their
nd, for example, nearby restaurants, gyms and cafes
to name just a few of a growing number of local search cat-
egories. Local search that takes into account the location of
the phone as
for the search is perhaps one of the most
exciting, popular and useful mobile applications today.
Existing mobile local search engines perform well when used
for a particular narrow range of queries where the relevance
Permission to make digital or hard copies of all or part of this work for
personal or classroom use is granted without fee provided that copies are
not made or distributed for pro
t or commercial advantage and that copies
bear this notice and the full citation on the
rst page. To copy otherwise, or
republish, to post on servers or to redistribute to lists, requires prior speci
permission and/or a fee.
, Sep 26-Sep 29, 2010, Copenhagen, Denmark.
Copyright 2010 ACM 978-1-60558-843-8/10/09.