In the online world, user engagement refers to the quality of the user experience that emphasizes the positive aspects of the interaction with a web application and, in particular, the phenomena associated with wanting to use that application longer and frequently. User engagement is a multifaceted, complex phenomenon; this gives rise to a number of potential approaches for its measurement. Common ways of measuring user engagement include: self-reporting (e.g., questionnaires); observational methods (e.g., facial expression analysis, speech analysis, desktop actions); and web analytics using online behavior metrics that assess users’ depth of engagement with a site. These methods represent various tradeoffs between the scale of data analyzed and the depth of understanding. For instance, surveys are small-scale but deep, whereas clicks can be collected on a large-scale but provide shallow understanding. However, little is known in validating and relating these types of measurement. This talk will present various efforts aiming at combining techniques from web analytics (in particular clicks) and existing works on user engagement coming from the domains of information science, multimodal human computer interaction and cognitive psychology.
This is a revised presentation of a keynote given at TPDL 2012. New work include online multi-tasking and exploring mouse movement.
COMPUTER 10: Lesson 7 - File Storage and Online Collaboration
Measuring Web User Engagement: a cauldron of many things.
1. Measuring Web User Engagement:
a cauldron of web analytics, focus attention,
positive affect, user interest, saliency,
mouse movement & multi-tasking
Mounia Lalmas
Yahoo! Labs
Barcelona
3. Click-through rate as proxy of
relevance!
Multimedia search
activities often
driven by
entertainment
needs, not by
M. Slaney, Precision-Recall Is Wrong for Multimedia, IEEE Multimedia Magazine, 2011.
information needs
4. Click-through rate as proxy of user
user satisfaction!
I just wanted the phone number … I am totally satisfied
5. In this talk – results, messages
& questions
1. Big data and in-depth focused user studies “a
must”!
2. Users “multi-task” online, what does this
mean?
3. Mouse movement hard to “experiment with”
and/or “interpret”.
4. Using crowd-sourcing “I think” worked fine.
6. This talk is not about aesthetics
… but see later
http://www.lowpriceskates.com/ (e-commerce – skating)
Source: http://www.webpagesthatsuck.com/
7. This talk is not about usability
http://chiptune.com/ (music repository)
Source: http://www.webpagesthatsuck.com/
8. User Engagement – connecting three sides
User engagement is a quality of the user experience
that emphasizes the positive aspects of interaction – in
particular the fact of being captivated by the technology.
Successful technologies are not just used, they are
engaged with.
user feelings: happy, sad, user mental states: concentrated, user interactions: click, read
excited, … lost, involved, … comment, recommend, buy, …
The emotional, cognitive and behavioural connection
that exists, at any point in time and over time, between a
user and a technological resource
S. Attfield, G. Kazai, M. Lalmas and B. Piwowarski. Towards a science of user engagement (Position Paper),
WSDM Workshop on User Modelling for Web Applications, 2011.
9. Characteristics of user engagement
Focused Attention Novelty
Positive Affect Richness & Control
Aesthetics
Reputation, Trust &
Expectation
Endurability
Motivation,
Interests, Incentives
& Benefits
H.L. O'Brien. Defining and Measuring Engagement in User Experiences with Technology. PhD Thesis,
2008.
H.L. O'Brien & E.G. Toms. JASIST 2008, JASIST 2010.
11. Connecting three measurement approaches
nt
ageme
ti on eng
interac
USER ENGAGEMENT
self-
repo
r te d en
gage ment
m en
t n gage
e
n it ive
cog
12. Models of user engagement …
towards a taxonomy?
nt
ageme
ti on eng
interac
USER ENGAGEMENT
self-
repo
r te d en
gage ment
m en
t n gage
e
n it ive
cog
13. Models of user engagement
Online sites differ concerning their engagement!
Games Search
Users spend Users come
much time per frequently and do
visit not stay long
Social media Special
Users come Users come on
frequently and average once
stay long
Service News
Users visit site, Users come
when needed periodically
14. Data and Metrics
Interaction data, 2M users, July 2011, 80 US sites
Popularity #Users Number of distinct users
#Visits Number of visits
#Clicks Number of clicks
Activity ClickDepth Average number of page views per visit.
DwellTimeA Average time per visit
Loyalty ActiveDays Number of days a user visited the site
ReturnRate Number of times a user visited the site
DwellTimeL Average time a user spend on the site.
15. Methodology
General models Time-based models
Dimensions weekdays, weekend
8 metrics 8 metrics per time span
#Dimensions 8 16
Kernel k-means with
Kendall tau rank correlation kernel
Nb of clusters based on eigenvalue distribution of kernel matrix
Significant metric values with Kruskal-Wallis/Bonferonni
#Clusters
(Models) 6 5
Analysing cluster centroids = models
16. Models of user engagement
[6 general]
• Popularity, activity and loyalty are independent from each other
• Popularity and loyalty are influenced by external and internal factors
e.g. frequency of publishing new information, events, personal
interests
• Activity depends on the structure of the site
interest-specific
periodic
media
e-commerce
media (daily)
search
models based on engagement metrics only
17. Time-based [5 models]
Models based on engagement over weekdays and weekend
work-related
daily news
hobbies,
interest-specific
weather
time-based models ≠ general models
next put all and more together! let machine learning tell you more!
18. Models of user engagement –
Recap & Next
User engagement is complex and standard
metrics capture only a part of it
User engagement depends on time (and users)
First step towards a taxonomy of models of user
engagement … and associated metrics
Next
More sites, more models
User demographics, time of the day, geo-location,
etc.
Online multi-tasking
J. Lehmann, M. Lalmas, E. Yom-Tov and G. Dupret. Models of User Engagement, UMAP 2012.
19. Online multi-tasking
nt
ageme
ti on eng
interac
USER ENGAGEMENT
self-
repo
r te d en
gage ment
m en
t n gage
e
n it ive
cog
20. Online multi-tasking
181K users, 2 months browser
data, 600 sites, 4.8M sessions
•only 40% of the sessions have
no site revisitation
•hyperlinking, backpaging and
teleporting
leaving a site is
not a “bad thing!”
(fictitious navigation between sites within an online session)
users spend more and more of their online session multi-tasking, e.g. emailing,
reading news, searching for information ONLINE MULTI-TASKING
navigating between sites, using browser tabs, bookmarks, etc
seamless integration of social networks platforms into many services
21. Navigating between sites –
hyperliking, backpaging and teleporting
Number of backpaging actions is an under-estimate!
23. Online multi-tasking – Some results
48% sites visited at least 9 times
Revisitation “level” depends on site
10% users accessed a site 9+ times (23% for search
sites); 28% at least four times (44% for search sites)
Activity on site decreases with each revisit but
activity on many search and adult sites increases
Backpaging usually increases with each revisit but
hyperlinking remains important means to navigate
between sites
24. Online multi-tasking –
Recap & Next
J. Lehmann, M. Lalmas & G. Dupret. Online Multi-Tasking and User Engagement. Submitted for publication, 2013.
25. Focus attention, positive affect & saliency
nt
ageme
ti on eng
interac
USER ENGAGEMENT
self-
repo
r te d en
gage ment
m en
t n gage
e
n it ive
cog
26. Saliency, attention and positive affect
How the visual catchiness (saliency) of
“relevant” information impacts user
engagement metrics such as focused
attention and emotion (affect)
focused attention refers to the exclusion of
other things
affect relates to the emotions experienced
during the interaction
Saliency model of visual attention
developed by Itti and Koch
L. Itti and C. Koch. A saliency-based search mechanism for overt and covert shifts of visual
attention. Vision Research, 40, 2000.
28. Study design
8 tasks = finding latest news or headline on celebrity or
entertainment topic
Affect measured pre- and post- task using the Positive
e.g. “determined”, “attentive” and Negative e.g. “hostile”, “afraid”
Affect Schedule (PANAS)
Focused attention measured with 7-item focused
attention subscale e.g. “I was so involved in my news tasks that I
lost track of time”, “I blocked things out around me when I was
completing the news tasks” and perceived time
Interest level in topics (pre-task) and questionnaire
(post-task) e.g. “I was interested in the content of the web pages”,
“I wanted to find out more about the topics that I encountered on the
web pages”
189 (90+99) participants from Amazon Mechanical Turk
29. Saliency and positive affect
When headlines are visually non-salient
users are slow at finding them, report more
distraction due to web page features, and show a
drop in affect
When headlines are visually catchy or
salient
user find them faster, report that it is easy to
focus, and maintain positive affect
Saliency is helpful in task performance,
focusing/avoiding distraction and in
30. Saliency and focused attention
Adapted focused attention subscale from the online
shopping domain to entertainment news domain
Users reported “easier to focus in the salient
condition” BUT no significant improvement in the
focused attention subscale or differences in
perceived time spent on tasks
User interest in web page content is a good
predictor of focused attention, which in turn is a
good predictor of positive affect
31. Saliency and user engagement –
Recap & Next
Interaction of saliency, focused attention,
and affect, together with user interest, is
complex
Next:
include web page content as a quality of user
engagement in focused attention scale
more “realistic” user (interactive) reading
experience
bio-metrics (mouse-tracking, eye-tracking, facial
expression, etc)
L. McCay-Peet, M. Lalmas, V. Navalpakkam. On saliency, affect and focused attention, CHI 2012
32. Mouse tracking, positive effect, attention
nt
ageme
ti on eng
interac
USER ENGAGEMENT
self-
repo
r te d en
gage ment
m en
t n gage
e
n it ive
cog
33. Mouse tracking … and user engagement
324 users from Amazon Mechanical Turk
(between subject design)
Two domains (BBC and Wikipedia)
Two tasks (reading and quiz)
“Normal vs Ugly” interface
Questionnaires (qualitative data)
focus attention, positive effect, novelty, interest,
usability, aesthetics
+ demographics, handeness & hardware
Mouse tracking (quantitative data)
movement speed, movement rate, click rate, pause
length, percentage of time still
36. Mouse tracking can tell about
Age
Hardware
Mouse
Trackpad
Task
Searching: There are many different types of phobia. What is
Gephyrophobia a fear of?
Reading: (Wikipedia) Archimedes, Section 1: Biography
38. Mouse tracking and user engagement —
Recap & Next
High level of ecological validity
Age, task, and hardware
Do we have a Hawthorne Effect???
“Usability” vs engagement
“Even uglier” interface? I don’t think so
Within- vs between-subject design?
Next
Sequence of movements
Automatic clustering
D. Warnock and M. Lalmas. An Exploration of Cursor tracking Data. Submitted for publication, 2013.
40. Thank you
Collaborators:
Ioannis Arapakis
Ricardo Baeza-Yates
Georges Dupret
Janette Lehmann
Lori McCay-Peet (Dalhousie University)
Vidhya Navalpakkam
David Warnock (Glasgow University)
Elad Yom-Tov
Contact: mounia@acm.org
and many others at Yahoo! Labs