|CrowdScanning Android Apps
| Mobile smartphone apps can make use of a smartphone's numerous capabilities — including network access, data storage, and sensors detecting motion, location, and sound level — and personal data, such as one's call logs and contacts list. These capabilities allow developers to create rich and compelling applications, but can also lead to new kinds of spyware, malware, and privacy intrusions. Our goal is to (a) develop a series of scalable techniques that combine crowdsourcing with static and dynamic analysis, to understand what mobile apps are really doing, and (b) design and evaluate better ways of communicating these behaviors to end-users.
| See our Ubicomp 2012 paper examining the feasibility of using crowdsourcing to evaluate privacy policies.
|Making Sense of User Feedback in a Mobile App Store
User review is a crucial component of open mobile app markets such as the Google Play Store. How do we summarize
hundreds or thousands of user reviews and identify the reasons of their likes/dislikes? Unfortunately, beyond simple
summaries such as histograms of user ratings, there are few
analytic tools that can provide insights into user reviews.
In this project, we analyze tens of millions user ratings and comments in mobile
app markets at three different levels of detail. Our system
is able to (a) discover inconsistencies in reviews; (b) identify
reasons why users like or dislike a given app, and provide
an interactive, zoomable view of how users' reviews evolve
over time; and (c) provide valuable insights into the entire
app market, identifying major user concerns and preferences
of different types of apps. We evaluated our techniques on a large dataset of 32 GB consisting of over 13
million user reviews of a total 171 thousand Android apps
in the Google Play Store. We discuss how the techniques
presented herein can be deployed to help a mobile app market operator such as Google Play as well as individual app
developers and end-users.
See our KDD 2013 paper on this project.
|Cross-cultural Privacy Study
While prior studies have provided us with an initial understanding of people’s location-sharing privacy preferences, they have been limited to Western countries and have not investigated the impact of the granularity of location disclosures on people’s privacy preferences. We report findings of a three-week comparative study collecting location traces and location-sharing preferences from two comparable groups in the U.S. and China. Results of the study shed further light on the complexity of people’s location-sharing privacy preferences and key attributes influencing willingness to disclose locations to others and to advertisers. While our findings reveal many similarities between U.S. and Chinese participants, they also show interesting differences, such as differences in willingness to share location at ‘home’ and at ‘work’ and differences in the granularity of disclosures people feel comfortable with. We conclude with a discussion of implications for the design of location-sharing applications and location-based advertising.
Paper will be appear in PUC journal soon.
|Context Extraction and Utilization for Mobile Wellness System (collaborate with docomo USA labs)
|This project focus on monitoring users' wellness condition through commodity mobile devices and providing relevant advices on wellness related activities. By systematically managing the various embeded sensors on smart phones, our system could accurately recognize users status and activity. Advices on activities, diet, medication and etc. will be automatically generated based on real-time context information in a non-intrusive way to help users form healthy habits.
|Exploring the Implications of Social-driven vs. Purpose-driven Location Sharing (collaborate with Karen Tang)
Karen Tang, Jialiu Lin and Jason Hong, “Rethinking Location Sharing: Exploring the Implications of Social-Driven vs. Purpose-Driven Location Sharing”, Proc. Of the 12th ACM International Conference on Ubiquitous Computing, Copenhagen, Denmark, 2010
|Automatic Place Naming
Many existing location sharing applications provide
coordinate-based location estimates and display them on a
map. However, people use a rich variety of terms to convey
their location to others, such as “home”, “Starbucks”, or
even “the bus stop near my apartment”. Our long-term goal
is to create a system that can automatically generate useful
place names based on real-time context. Towards this end,
we conducted a series of user studies to understand people’s preferences for place
Based on the results, we propose a hierarchical classification of place
naming methods. We further conclude that people’s place
naming preferences are complex and dynamic, but fairly
predictable by using machine learning techniques. Our fndings also suggested that two factors,
people’s routine and their willingness to share location
information, strongly influence the way people name a
place. The new findings provide important implications for
location sharing applications and other location based
Jialiu Lin, Guang Xiang, Jason Hong and Norman Sadeh, “Modeling People’s Place Naming Preferences in Location Sharing”, Proc. Of the 12th ACM International Conference on Ubiquitous Computing, Copenhagen, Denmark, 2010
|Energy Efficient Mobile Sensing System (collaborate with Yi Wang)
Urban sensing, participatory sensing, and user activity recognition
can provide rich contextual information for mobile
applications, such as mobile social networking and location-based
services. However, continuously capturing this contextual
information on mobile devices consumes a huge amount of energy.
We proposed a novel framework
for an Energy Efficient Mobile Sensing System (EEMSS).
EEMSS uses hierarchical sensor management strategies to
recognize user states and detect state transitions.
By powering only a minimum set of sensors and using appropriate
sensor duty cycles EEMSS significantly improves
device battery life. We also implement a mobile user state recognition system that automatically identifies a
set of users’ daily activities in real time. Our evaluation showed that our approach
the device battery life by more than 75% while maintaining
both high accuracy and low latency in recognizing
transitions between end-user activities.
This work was collaborated with Nokia Research Center at Palo Alto, CA and USC.
Yi Wang, Jialiu Lin, Murali Annavaram, Quinn A. Jacobson, Jason Hong, Bhaskar Krishnamachari and Norman Sadeh, “A Framework of Energy Efficient Mobile Sensing for Automatic User State Recognition,” Proc. of the 7th Annual International Conference on Mobile Systems, Applications and Services, Krakow, Poland, June 22-25, 2009
Planning and attending social events are a part of our everyday lives. However, current
software does not support all the activities surrounding social events. In particular,
while there are many web‐based social event sites that are good for planned events
(such as evdb.com, zvents.com, upcoming.org, eventful.com, and SonicLiving), there is
little support for ad hoc and impromptu events, for example events that are happening
right now (e.g. “free food now”) or later in the day (e.g. “bowling later today?” or
“dinner in 15 minutes?”). There is also another implicit issue of this problem, namely
that these web sites were designed with the expectation that people would interact
with them via desktop computers. Since people are not always at their desktops, this
constraint limits spur of the moment decisions to find and attend events. Similarly, constraining ourselves
to the desktop computer limits how we share events with friends.
To address this problem, we are developing WhisperMobile, a mobile social application
that facilitates creating, finding, and sharing impromptu social events. WhisperMobile
lets people create new impromptu events as well as find nearby events that others have
posted, and then organize friends to go to that event.
|Locaccino --- User Controllable Security and Privacy
A number of mobile applications have emerged that allow users to locate one another.
However, people have expressed concerns about the privacy implications associated
with this class of software, which suggests that these kinds of applications can only be
broadly adopted if these concerns are adequately addressed.
Locaccino, developed by Mobile Commerce Lab, is an application that enables cell
phone and laptop users to selectively share their locations with others (e.g. friends,
family, and colleagues). Users interact with their devices to inquire about the locations
of other users and to create privacy and obfuscation policies that govern how their own
location information may be accessed.
The objective of our work has been to better understand people’s attitudes and
behaviors towards privacy as they interact with such an application, and to explore
technologies that empower users to more effectively and efficiently specify their privacy
preferences (or “policies”). These technologies include user interfaces for specifying
rules and auditing disclosures, and also include machine learning techniques to refine
user policies based on their feedback.