Identification of user confusion in a web application Author: Michal Hucko Supervisor: prof. Mária Bieliková ”Confusion is a situation in which people are uncertain about what to do or are unable to understand something clearly.” Histogram representation of features Mouse movements Extracted features velocity, acceleration, distance, duration, jerk, ... Confusion classifier If user confused, show guides Predict user confusion in real time for web applications based on logged mouse interaction data Goal • 6 tasks at FiroTour travel agency’s portal • 59 participants • confusion was logged with a software button (exclamation mark) situated in the right top corner of the screen • 95 out of 354 tasks with button press Eyetracking user study Results • 99% precision on not confused data (real time) • 40% precision on confused data (real time) • 94% precision on not confused data (prediction after session) • 40% precision on confused data (prediction after session) We compared logistic regression, random forest and multilayer perceptron classifier. Our method is part of an ongoing commercial project YesElf. We implemented a production ready module able to predict the confusion in real time. Hundreds of YesElf’s customers can use our solution daily. YesElf Mouse features • Horizontal velocity • Vertical velocity • Velocity • Acceleration • Distance • Jerk • Num. of movements

Identification of user confusion in a web application · Identification of user confusion in a web application Author:Michal Hucko Supervisor:prof. Mária Bieliková ”Confusion

Download PDF Report

Upload
others
View
0
Download
0

Embed Size (px)

Citation preview

Page 1: Identification of user confusion in a web application · Identification of user confusion in a web application Author:Michal Hucko Supervisor:prof. Mária Bieliková ”Confusion

IdentificationofuserconfusioninawebapplicationAuthor:MichalHuckoSupervisor: prof.MáriaBieliková

”Confusionisasituationinwhichpeopleareuncertainaboutwhattodoorareunabletounderstandsomethingclearly.”

Histogram representation

of features

Mouse movements

Extracted features

velocity, acceleration, distance,

duration, jerk, ...

Confusion

classifier

If user confused,

show guides

Predict user confusion in real time for webapplications based on logged mouse interactiondata

Goal

• 6 tasks at FiroTour travel agency’s portal• 59 participants• confusionwasloggedwithasoftwarebutton

(exclamationmark)situatedintherighttopcornerofthescreen

• 95 out of 354 tasks with button press

Eyetrackinguserstudy

Results• 99% precision on not confused data (real time)• 40% precision on confused data (real time)• 94% precisiononnotconfuseddata

(predictionaftersession)• 40% precisiononconfuseddata

(predictionaftersession)Wecomparedlogisticregression,randomforestandmultilayerperceptron classifier.

Our method is part of an ongoing commercial projectYesElf. We implemented a production ready module ableto predict the confusion in real time. Hundreds of YesElf’scustomers can use our solution daily.

YesElf

Mousefeatures• Horizontal velocity• Vertical velocity• Velocity• Acceleration• Distance

• Jerk• Num. of movements