The Future of Search (Keynote at I-Know 2010)

Future Trends in Search User Interfaces Dr. Marti Hearst UC Berkeley i-Know Conference Keynote Sept 1, 2010

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

Forecasting the Future First: What are the larger trends? In technology? In society? Next: Project out from these.

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

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

Trend: More Natural Queries

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

A recent example: keywords failed 7

Instead, ask as a question 8

And: find an answer 9

Advanced user interface design 10

Trend: More Natural Queries • Blend two ideas: • “sloppy commands” • predictions based on user behavior data • This behavior is subtly and steadily increasing in sophistication across many interfaces. 11

Sloppy Commands • Like command languages, but • the user has a lot of flexibility in expression • so memorization is not required • “time graz” “what time is it in graz” “graz time now” 12

Sloppy Commands + Visual Feedback • Can include rich visual feedback • Quicksilver in Apple • Inky by Miller et al. 13

Sloppy Commands + Rich Data • Combine Mozilla’s Ubiquity and Freebase to make a flexible predictive query engine • By spencerwaterbed: http://vimeo.com/13992710 14

Sloppy Commands + Rich Data • Combine Mozilla’s Ubiquity and Freebase to make a flexible predictive query engine • By spencerwaterbed: http://vimeo.com/13992710 15

Far Future Trend: Dialogue • We’re still far away. • SIRI is promising as a move forward; based on state-of-the-art research. 16

Trend: Social Search People are Social; Computers are Lonely. Don’t Personalize Search, Socialize it!

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

Trend: Social Search • Socially motivated ranking of search results • Explicitly recommended • Digg, StumbleUpon • Delicious, Furl • Google’s SearchWiki • Implicitly recommended • Click-through • People who bought… • Yahoo’s MyWeb (now Google Social Search) 19

Social Search: Implicit Suggestions • Human-generated suggestions (augmented with statistics) still beat purely machine- generated ones. • Spelling suggestions • Query term suggestions (“search as you type”) • Recommendations (books, movies, etc) • Ranking (using clickthrough statistics) 20

Social Search: Asking for Answers What do people ask of their social networks? Type % Example Building a new playlist – 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

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

Social Search: Seeing info that people you know have seen • Yahoo MyWeb, Google Social Search 23

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

Social Search: People Collaborating Tools to help with this are only just beginning. Pickens et al., SIGIR 2008 25

Future Trend: The Decline of Text • Or: the rise of audio/video • The “cultural heavy lifting” (in America at least)is moving from text to audio and video. (Full essay at http://edge.org/q2009/q09_9.html#hearst) 26

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 “responses” 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

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

Future Trend: The Decline of Text and Rise of Audio/Video • Other advantages • Doesn’t 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

Future Trends … not so much? • Personalization • Visualization … some breakthroughs are needed. 29

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 peoples’ heads. 30

Thank you! Marti Hearst UC Berkeley Book full text freely available at: http://searchuserinterfaces.com

The Future of Search (Keynote at I-Know 2010)

by marti_hearst on Sep 06, 2010

Accessibility

Categories

Tags

Upload Details

Usage Rights

Statistics

The Future of Search (Keynote at I-Know 2010) — Presentation Transcript