• UCSB_GradPost twitter avatar
    Mentor a STEM intern this summer https://t.co/efvOXzX8ot #UCSB #ucsbgradpost
    51 min 56 sec ago
  • UCSB_GradPost twitter avatar
    'Into the Beautiful North' discussion on March 2 https://t.co/ZngcgQCGsG #UCSB #ucsbgradpost
    51 min 56 sec ago
  • ArtsandLectures twitter avatar
    Beauty and the Bizarre: Hummingbirds, Bees, Bats and Zombie Parasites https://t.co/gdEIBSIXDA
    1 hour 58 min ago
  • AS_UCSB twitter avatar
    Get Cozy with AS. Join us for our winter recruitment fair and interact with active AS. members. Today 6-8pm Loma Pe… https://t.co/FJeNqZxZJ1
    2 hours 54 min ago
  • ArtsandLectures twitter avatar
    Grammy Award-winning octet @roomfulofteeth brings its singing traditions to Hahn Hall on Wednesday, Apr 26 at 7PM!… https://t.co/IrhE1Thez3
    4 hours 18 min ago
  • ArtsandLectures twitter avatar
    Join @BanffMtnFest on a thrilling journey through exotic mountains, tonight at 7:30PM at the Arlington Theatre!… https://t.co/FJSBWoI4Tq
    5 hours 28 min ago
  • UCSBgauchos twitter avatar
    .@UCSB_Baseball falls 4-1 to St. Mary's in first home midweek. Gauchos fly to Kentucky for 3 this weekend. RECAP >>… https://t.co/i8gnZk9Lw9
    18 hours 21 min ago
  • UCSBgauchos twitter avatar
    Gauchos Close Strong to Finish 6th at Del Walker Intercollegiate https://t.co/dPC0rlkFEG
    18 hours 25 min ago
  • UCSBgauchos twitter avatar
    Winners of 2 Out of Last 3, Gauchos Head to Fullerton Thursday https://t.co/UtRgwenJ63
    19 hours 24 min ago
  • UCSBLibrary twitter avatar
    A moving collection- portraits of African American men & women from late 19th c. Available: https://t.co/RYyjXELvEw… https://t.co/n6YyPpcWTy
    20 hours 13 min ago
  • ArtsandLectures twitter avatar
    Get your @BanffMtnFest preview via @SBIndpndnt. #BanffIsBack #Banff https://t.co/JkmcxFaG9w
    21 hours 14 min ago

You Are What You Click

UCSB computer scientists embark on a National Science Foundation-funded project to model online user behavior
Tuesday, September 29, 2015 - 09:15
Santa Barbara, CA

Social media.jpg

Social media

Photo Credit: 

Matt Perko

Zhao2 tiny.jpg

Ben Zhao

Ben Zhao

Photo Credit: 

Spencer Bruttig

heather-aust.png

Heather Zheng

Heather Zheng

Photo Credit: 

Courtesy Image

It’s no secret that the things we click on, scroll across, swipe, tap or drag when we’re browsing online or using a smartphone application can yield valuable information about us. Such data is a veritable goldmine to web browsers and online retailers who use it to assess our preferences and target advertising to our tastes. But, researchers at UC Santa Barbara suggest that studying users’ online or smartphone actions could yield far more information about us than simply shopping habits.

With $499,949 in funding from the National Science Foundation, computer science professors Ben Zhao and Heather Zheng will investigate how these detailed, time-stamped logs of online and smartphone user actions, dubbed “clickstreams,” can reveal insights about users.

“We’re trying to build natural, data-driven models of user behavior, without external labels or preconceived categories, but rather from natural patterns in user behavior,” said Zhao. To do this, the researchers will analyze anonymized user action logs from Los Angeles-based smartphone app Whisper and Chinese social media site Renren. “By avoiding preset categories, we can identify real natural patterns that may be difficult to predict, while allowing for real unexpected surprises in user behavior,” he explained.

Using similarity graphs to compare the data from the multitudes of clickstreams, the scientists hope to identify general behavior patterns over time. This information can in turn be used to identify abnormal or unusual behaviors that could, for instance, indicate security risks.

“We’ve already done this successfully on LinkedIn and Renren to identify users using fake accounts to attack those systems,” said Zhao. “The resulting accuracy has been exceptional, and has detected attacks that we could not have predicted in advance, simply by noting how large groups of users act similarly to each other but unlike most normal users in the system.”

In the big picture, the researchers will also be investigating methods of making these clickstream graphs scalable to large user populations — in the hundreds of millions of users — as well as ways to tune the modeling system to different dimensions of user behavior or to specific applications.

Contact Info: 

Sonia Fernandez
(805) 893-4765
sonia.fernandez@ucsb.edu

Topics: