I made this talk in response to an invitation to give the opening keynote on the topic of the future of search interfaces at the i-Know conference in Graz, Austria, in Sept 2010: http://i-know.tugraz.at/
Repurposing LNG terminals for Hydrogen Ammonia: Feasibility and Cost Saving
Â
The Future of Search (Keynote at I-Know 2010)
1. Future Trends
in
Search User Interfaces
Dr. Marti Hearst
UC Berkeley
i-Know Conference Keynote
Sept 1, 2010
2. In some cases,
blended and Primarily search text
context-sensitive
Fast response time Search Support for
related queries
Interfaces and documents
today?
Navigation and Tailored to keyword
organization queries and iterating
support from on the information
faceted metadata
3
3. Forecasting the Future
First: What are the larger trends?
In technology?
In society?
Next: Project out from these.
4. Wide adoption of touch-
Latent preferences activated devices with
for audio and video excellent UI design
Wide adoption of
social media and
user-generated Increasingly
Natural available rich,
integrated data
Interfaces sources
Improvements in Wide adoption of
NLP, speech mobile devices with
recognition via
huge data sets
3
5. Wide adoption of touch-
Latent preferences activated devices with
for audio and video excellent UI design
Wide adoption of
social media and
user-generated Increasingly
Natural available rich,
integrated data
Interfaces sources
Improvements in Wide adoption of
NLP, speech mobile devices with
recognition via
huge data sets
3
6. Wide adoption of touch-
Latent preferences activated devices with
for audio and video excellent UI design
Wide adoption of
social media and
user-generated Increasingly
Natural available rich,
integrated data
Interfaces sources
Improvements in Wide adoption of
NLP, speech mobile devices with
recognition via
huge data sets
3
7. Wide adoption of touch-
Latent preferences activated devices with
for audio and video excellent UI design
Wide adoption of
social media and
user-generated Increasingly
Natural available rich,
integrated data
Interfaces sources
Improvements in Wide adoption of
NLP, speech mobile devices with
recognition via
huge data sets
3
8. Wide adoption of touch-
Latent preferences activated devices with
for audio and video excellent UI design
Wide adoption of
social media and
user-generated Increasingly
Natural available rich,
integrated data
Interfaces sources
Improvements in Wide adoption of
NLP, speech mobile devices with
recognition via
huge data sets
3
9. Wide adoption of touch-
Latent preferences activated devices with
for audio and video excellent UI design
Wide adoption of
social media and
user-generated Increasingly
Natural available rich,
integrated data
Interfaces sources
Improvements in Wide adoption of
NLP, speech mobile devices with
recognition via
huge data sets
3
10. Wide adoption of touch-
Latent preferences activated devices with
for audio and video excellent UI design
Wide adoption of
social media and
user-generated Increasingly
Natural available rich,
integrated data
Interfaces sources
Improvements in Wide adoption of
NLP, speech mobile devices with
recognition via
huge data sets
3
12. Trend: Natural Interfaces
What does this mean for Search UIs?
⢠Longer, more natural queries
⢠Search that is as social as people are
⢠Deep integration of audio and video
⢠Dialogue and conversational (farther out)
4
14. Trend: Longer, more natural queries
⢠The research suggests people prefer to state their
information need rather than use keywords.
⢠But after first using a search engine they quickly learned that
full questions resulted in failure.
⢠Average query length continues to increase
⢠Major search engines are now handling long queries well.
⢠Information worded as questions is increasing on the
web.
⢠From social question-answering sites and forums.
6
19. Trend: More Natural Queries
⢠Blend two ideas:
⢠âsloppy commandsâ
⢠predictions based on user behavior data
⢠This behavior is subtly and steadily
increasing in sophistication across many
interfaces.
11
20. Sloppy Commands
⢠Like command languages, but
⢠the user has a lot of flexibility in expression
⢠so memorization is not required
⢠âtime grazâ âwhat time is it in grazâ âgraz time nowâ
12
21. Sloppy Commands + Visual Feedback
⢠Can include rich visual feedback
⢠Quicksilver in Apple
⢠Inky by Miller et al.
13
22. Sloppy Commands + Rich Data
⢠Combine Mozillaâs Ubiquity and Freebase to
make a flexible predictive query engine
⢠By spencerwaterbed: http://vimeo.com/13992710
14
23. Sloppy Commands + Rich Data
⢠Combine Mozillaâs Ubiquity and Freebase to
make a flexible predictive query engine
⢠By spencerwaterbed: http://vimeo.com/13992710
15
24. Far Future Trend: Dialogue
⢠Weâre still far away.
⢠SIRI is promising as a
move forward; based on
state-of-the-art research.
16
25. Trend: Social Search
People are Social; Computers are Lonely.
Donât Personalize Search, Socialize it!
26. Social Search
Implicit: Suggestions generated as
a side-effect of search activity.
Asking: Communicating
directly with others.
Explicit: knowledge accumulating via
the deliberate contributions of many.
Collaborative: Working with
other people on a search task.
18
27. Trend: Social Search
⢠Socially motivated ranking of search results
⢠Explicitly recommended
⢠Digg, StumbleUpon
⢠Delicious, Furl
⢠Googleâs SearchWiki
⢠Implicitly recommended
⢠Click-through
⢠People who boughtâŚ
⢠Yahooâs MyWeb (now Google Social Search)
19
28. Social Search: Implicit Suggestions
⢠Human-generated suggestions (augmented
with statistics) still beat purely machine-
generated ones.
⢠Spelling suggestions
⢠Query term suggestions (âsearch as you typeâ)
⢠Recommendations (books, movies, etc)
⢠Ranking (using clickthrough statistics)
20
29. Social Search: Asking for Answers
What do people ask of their social networks?
Type % Example
Building a new playlist â any ideas for good running songs?
Recommendation 29%
I am wondering if I should buy the Kitchen-Aid ice cream maker?
Opinion 22%
Anyone know a way to put Excel charts into LaTeX?
Factual 17%
Rhetorical 14% Why are men so stupid?
Invitation 9% Who wants to go to Navya Lounge this evening?
Need a babysitter in a big way tonight⌠anyone??
Favor 4%
I am hiring in my team. Do you know anyone who would be interested?
Social connection 3%
Offer 1% Could any of my friends use boys size 4 jeans?
Morris et al., CHI 2010 21
30. Social Search: Explicit Help via
Question-Answering Sites
⢠Content is produced in a manner amenable to
searching for answers to questions.
⢠Search tends to work well on these sites and
on the internet leading to these sites
⢠Like an FAQ but
⢠with many authors, and
⢠with the questions that the audience really wants the
answers to, and
⢠written in the language the audience wants to use.
22
32. Social Search: Explicit Suggestions
Building Knowledge
⢠Social knowledge management tools seem promising
⢠Utilize the best of social networks, tagging, blogging,
web page creation, wikis, and search.
Millen et al., CHI 2006 24
33. Social Search: People Collaborating
Tools to help with this are only just beginning.
Pickens et al., SIGIR 2008 25
34. Social Search: People Collaborating
Tools to help with this are only just beginning.
Pickens et al., SIGIR 2008 25
35. Future Trend: The Decline of Text
⢠Or: the rise of audio/video
⢠The âcultural heavy liftingâ (in America at
least)is moving from text to audio and
video.
(Full essay at http://edge.org/q2009/q09_9.html#hearst) 26
36. Future Trend: The Decline of Text
⢠Or: the rise of audio/video
⢠Video and audio are now easy to produce and share.
⢠Pew: Use of video sharing sites doubled from
2006-2009
⢠YouTube: Video âresponsesâ apparently arose
spontaneously
⢠Videos for presidential debates were mundane.
⢠Millions of video views; no where near this
number for article readings
⢠Pew: Marketing emails with podcasts 20% more likely
to be opened.
⢠Movies with subtitles do poorly in the U.S.
⢠Newspaper web sites are starting to look like TV.
(Full essay at http://edge.org/q2009/q09_9.html#hearst) 26
37. Future Trend:
The Decline of Text and Rise of Audio/Video
⢠What is currently solved:
⢠Ease of creating and sharing videos
⢠What needs improvement:
⢠Editing tools
⢠The main impediments to more fully replacing text are:
⢠The need for better search and scanning of audio and video
⢠A means for silent audio input
⢠What about the popularity of texting?
⢠An interesting counter-trend
⢠Especially popular among youth
⢠Cheap
⢠Can be done surreptitiously
(Full essay at http://edge.org/q2009/q09_9.html#hearst) 28
38. Future Trend:
The Decline of Text and Rise of Audio/Video
⢠Other advantages
⢠Doesnât require literacy (but can serve as a bridge)
⢠Robust video devices to teach agricultural techniques
⢠What about the popularity of texting?
⢠An interesting counter-trend
⢠Especially popular among youth
⢠Cheap
⢠Can be done surreptitiously
(Full essay at http://edge.org/q2009/q09_9.html#hearst) 27
39. Future Trends ⌠not so much?
⢠Personalization
⢠Visualization ⌠some breakthroughs are
needed.
29
40. Summary
As algorithms get more sophisticated, we can
build search interfaces that allow people to
interact more naturally:
⢠More language-like queries
⢠Speaking & hearing rather than typing & reading
⢠Interacting with other people while doing search
tasks
⢠Leveraging the knowledge in peoplesâ heads.
30
41. Thank you!
Marti Hearst
UC Berkeley
Book full text freely available at:
http://searchuserinterfaces.com