modeling people’s place naming preferences in location sharing, at ubicomp2010
DESCRIPTION
Most location sharing applications display people's locations on a map. However, people use a rich variety of terms to refer to their locations, such as "home," "Starbucks," or "the bus stop near my house." Our long-term goal is to create a system that can automatically generate appropriate place names based on real-time context and user preferences. As a first step, we analyze data from a two-week study involving 26 participants in two different cities, focusing on how people refer to places in location sharing. We derive a taxonomy of different place naming methods, and show that factors such as a person's perceived familiarity with a place and the entropy of that place (i.e. the variety of people who visit it) strongly influence the way people refer to it when interacting with others. We also present a machine learning model for predicting how people name places. Using our data, this model is able to predict the place naming method people choose with an average accuracy higher than 85%. Authors are Jialiu Lin, Guang Xiang, Jason Hong, and Norman SadehTRANSCRIPT
Modeling People’s Place Naming Preferences in
Location Sharing
Jialiu Lin, Guang Xiang, Jason Hong, Norman SadehSchool of Computer Science
Carnegie Mellon University
Location Sharing Applications
Map based LSA
Semantic Gap
Map based LSA
We seldom say …• Hey mom, I am still at 55.66 north,
12.59 east. I will be home soon.• Let’s have some coffee at 417 S
Craig st.• I’m at 2039 Main st and already in
bed.
Instead, we say …• Hey mom, I am still at school. I will
be home soon.• Let’s have some coffee at Starbucks.• I’m at home and already in bed.
Why We Care about Place Names?
Provide more flexible and pertinent information Can infer not only position, but also activities,
availability, safety and etc. Multiple dimensions to tailor the information
Preserve privacy Obfuscate physical location e.g. sharing ‘Home’ instead of physical location of
home
Better Integration (vs. map) More information in smaller space
Location Sharing Applications
Map based LSA Check-in based LSA
Diversity of Place Naming
Check-in based LSA
What if I want to share different location names to different people?
I want to know I’m at work
I want to know I’m in the conference room.
I want to know I’m in RM 4221
……….
Goal and Objective
Ideally:
First Step: ← Focus of this paper
f( , , )loc pref →… Appropriate place name
f( , , )loc pref … Appropriate place naming method→
e.g:f(40.44,-79.94, ‘sister’, work day night,…) ‘grocery store’f(36.49,-79.22, ‘close friend’, weekend,…) ‘@ Starbucks’
e.g:f(40.44,-79.94,‘sister’, work day night,…) place’s functionalityf(36.49,-79.22, ‘close friend’, weekend,…) Business name
Outline
Empirical study of location naming 2 weeks study with 26 participants in 2 cities
Result analysis Place naming diversity Taxonomy on location naming methods Modulated location information Influencing factors in place naming Predictive model of place naming methods
▪ Top level accuracy 93%▪ Sub level accuracy 68%▪ Granularity accuracy 89%
Discussion and conclusion
Empirical Study Overview
Time: August 2009 Duration: Two weeks Number of participants: 26
12 female, 14 male Age 20-44, mean=25.6
Locations: CMU Pittsburgh campus (18) CMU Silicon Valley campus (8)
Entrance survey: List names under different social groups
In study: Mobile application recorded participants location
information (GPS+ wifi) Participants uploaded this information through
our web application every day Participants answered a set of question regarding
to the places they had been. Exit survey:
General attitudes toward location sharing
Procedure
12
You were observed at this location from 15:35 Aug 12 (Wed) to 16:24 Aug 12 (Wed) • Maps reminds participants of
the locations they visited.
• Questions were asked for four social groups • family member, • close friend, • acquaintance, • stranger.
Imagine that Mary (your family member) wanted to know where you were at the given time period.
1.How comfortable would you be to let her know where you were at this time?
1:not comfortable at all, 7: extremely comfortable
2.How familiar is Mary with this location? 1: not familiar at all, 7: extremely familiar
3. What terms or phrases (place name) would you use to refer to this location if you want to tell her where you were?
Results Analysis
Place naming diversity Taxonomy on location naming methods Modulated location information Influencing factors in place naming Predictive model of place naming methods
Place Naming Diversity
403 distinct locations identified 1157 location names observed
2.8 names per location. (SD=0.89, med=3, max=7, min=1)
28
150
109
89
223 2
160
120
80
40
0
1 2 3 4 5 6 7
# of place names
Place Naming Taxonomy
Taxonomy on Place Naming Method
Place Names
Hybrid
Top Level
e.g. :home, work, friend’s house…
e.g. :gym, restaurant, grocery store…
e.g. :McDonalds, Hilton…
Semantic
Personal FunctionalBusiness
name
Geographic
Sub Level
Address Landmark
e.g. :5000 Forbes ave,Rued Langgaards Vej, 2300 København…
e.g. :near the Liberty Bridge,outside city library…
Place Naming Taxonomy
Place Names
Hybrid
Top Level
Semantic Geographic
Granularity
State
CityRegion
Neighborhood
StreetIntersectio
n
HouseBuilding
FloorRoom
e.g. Pennsylvania e.g. Wean Hall 4119… …
Modulated Location Information
Semantic 74.2%
Geographic
31.8%
Hybrid6.0%
40%
30%
20%
10%
0%
8.5%
state cityregion
neighborhoodintersection
streethouse
buildingfloorroom
35.7%
16.0% 19.1% 19.3%
1.4%
Blurring: People have the tendency to make their location info unlocatable
cannot pinpoint
Pattern 2: Modulate Location Information
Personal47.1%
Functional12.8%
Business name9.3%
Landmark1.3%
Address23.6%
Hybrid6.0%GEOGRAPHIC
SEMANTIC
Distilling: Viewer of this information extract physical position by using shared knowledge
Influencing Factors
Social Relation Privacy Concern
Recipient’s familiarity Place Entropy
Influencing Factors
Social Relation Privacy Concern
Recipient’s familiarity Place Entropy
Closer Relationship leads to more semantic sharing, finer granularity
Granularity
Top Categories
Influencing Factors
Social Relation Privacy Concern
Recipient’s familiarity Place Entropy
More comfortable: more semantic sharing, finer granularity
Influencing Factors
Social Relation Privacy Concern
Recipient’s familiarity Place Entropy
Familiarity: non-linear influencing factor
Influencing Factors
Social Relation Privacy Concern
Recipient’s familiarity Place Entropy
Higher entropy: less semantic sharing, finer granularity
Predictive Model of Place Naming Methods
• 14 different attributes direct captured or derived attributes, 3 labels• Attributes: e.g. social relation (1-4), frequency,
comfort level(1-7), familiarity (1-7), place entropy, duration (in sec), arriving time, physical distance, and etc…
• Labels: top level category label, sub category label, granularity label
• Use Weka 3 as the major tool• Training and testing data separated by participant ID
• Randomly select 5 participants as testing• Remaining as training
• Results averaged over 50 rounds
Accuracy%J48 Decision Tree
Support Vector Regression Naive Bayes
Top level category
85.50 (3.14)
76.21(4.27)
80.33(3.51)
Sub-Class 60.74 (1.50)
54.26(3.34)
56.19(1.93)
Granularity 71.25 (3.44)
68.55(4.58)
67.48(2.67)
Predictive Model of Place Naming Methods
Accuracies tend to plateau after one week
Accuracy can be boosted when learn from similar people
• Calculate similarity (Kappa value) among participants based on their exit survey
Accuracy% MaxTop level category
93.2
Sub-Class 67.8
Granularity 88.7
Study Limitations
Participants from one university community
No real sharing happened during study
Conclusion
Conducted empirical study on how people name places in different context
Proposed taxonomy of place naming methods
Identified several typical patterns Place naming diversity Location information Modulation Significant influencing factors: social
relation, privacy, familiarity, place entropy.
Conclusions
Used machine learning to predict place naming methods Top categories accuracy 93% Sub categories accuracy 68% Granularity accuracy 89%
Thank you!
Q & A
Attributes
Explanations
(lat, lon) Geo-coordinates of the placeFromTime P’s arrival time to the place ToTime P’s departure time from the placeGroup The social group of R (Family member, close
friend, acquaintance, or stranger)PhyDist The physical distance between P and R, in a
scale of 1 to 4 (1=same city, 2=same state diff cities, 3=same country diff states, and 4=diff countries).
CmftShare How comfortable of P letting R know where he/she was at that moment, in a scale of 1 to 7 (1= not comfortable at all, 7= fully comfortable)
Familiarity How familiar R with this place, in a scale of 1 to 7 (1=don’t know this place, 7=extremely familiar. P can input “not sure” if they don’t know the answer)
PlaceName The place name which P would like to use in the specific scenario.
Attributes ExplanationsDistHome Distance from this place to P’s homeDistWork Distance from this place to P’s work placeDuration The amount of time P spent at this placeFreq Number of times P visited this place UserCount Number of participants who visited this
placeEntropy * The diversity of users visiting a particular
place.
* J. Cranshaw, E. Toch, J. Hong, A. Kittur, and N. Sadeh, "Bridging the Gap Between Physical Locaation and Online Social Networks," in Proc. UbiComp, 2010
Derived AttributesAppendix