Soylent: A Word Processor with a Crowd Inside

SoylentA Word Processor with a Crowd InsideMichael Bernsteinmsbernst@csail.mit.eduGreg Little, Rob Miller, David Karger, David Crowell, Katrina Panovichmit csailBjörn Hartmann Mark Ackermanucberkeley university of michiganmit human-computer interaction

Shortening A Paper to Ten Pages1) Do it yourself2) Use an AI3) Ask colleagues

Shortening A Paper to Ten Pages4) Recruit a crowd

Soylent is a word processing interface that uses crowd contributions to aid complex writing tasks.

Soylent is a word processing interface that uses crowd contributions to aid complex writing tasks.Soylent is people.Amazon Mechanical Turk Soylent’s core algorithms are human-powered.Find Unnecessary TextRequester:Matt C.Reward:$0.01Tasks Available: 7Shorten Rambling TextRequester:Gordon L.Reward:$0.04Tasks Available: 12

Soylent is a word processing interface that uses crowd contributions to aid complex writing tasks.Find-Fix-Verify:Crowd control design patternFind a problemFix each problemVerify quality of each fixSoylent, a prototype...Soylent, a prototype...Soylent, a prototype...Soylent, a prototype...

Embed paid crowd workers in user interfaces to support cognition and manipulation tasks on demand

Word processors don’t:- parse semantics well judge qualityPaid crowds don’t:- guarantee quality- control costsState ofthe Art[Kittur ’08]

Paid crowds can:- parse semantics well judge qualitySoylent can:- guarantee quality- control costsWord witha Crowd Inside

Challenges in Programming CrowdsThis project has interacted with~9000 Turkers on ~2000 different tasksKey Problem: crowd workers often produce poor output on open-ended tasks30% Rule: ~30% of the resultsfrom open-ended tasks will be unsatisfactoryIntroductionDemoFind-Fix-VerifyEvaluationDiscussionSoylent

Two Personas: An ExampleProofread and correct the following paragraph:The theme of loneliness features throughout many scenes in Of Mice and Men and is often the dominant theme of sections during this story. This theme occurs during many circumstances but is not present from start to finish. In my mind for a theme to be pervasive is must be present during every element of the story. There are many themes that are present most of the way through such as sacrifice, friendship and comradship. But in my opinion there is only one theme that is present from beginning to end, this theme is pursuit of dreams.

The theme of loneliness features throughout many scenes in Of Mice and Men and is often the dominant theme of sections during this story. This theme occurs during many circumstances but is not present from start to finish. In my mind for a theme to be pervasive is must be present during every element of the story. There are many themes that are present most of the way through such as sacrifice, friendship and comradship. But in my opinion there is only one theme that is present from beginning to end, this theme ispursuit of dreams. Two Personas: An ExampleProofread and correct the following paragraph:

The Lazy TurkerDoes as little work as necessary to be paidThe theme of loneliness features throughout many scenes in Of Mice and Men and is often the dominant theme of sections during this story. This theme occurs during many circumstances but is not present from start to finish. In my mind for a theme to be pervasive is must be present during every element of the story. There are many themes that are present most of the way through such as sacrifice, friendship and comradship. But in my opinion there is only one theme that is present from beginning to end, this theme ispursuit of dreams.

The Lazy TurkerDoes as little work as necessary to be paidThe theme of loneliness features throughout many scenes in Of Mice and Men and is often the dominant theme of sections during this story. This theme occurs during many circumstances but is not present from start to finish. In my mind for a theme to be pervasive is must be present during every element of the story. There are many themes that are present most of the way through such as sacrifice, friendship and comradeship. But in my opinion there is only one theme that is present from beginning to end, this theme ispursuit of dreams.

The Eager BeaverGo beyond task requirements to be helpful, but introduce errors in the processThe theme of loneliness features throughout many scenes in Of Mice and Men and is often the dominant theme of sections during this story. This theme occurs during many circumstances but is not present from start to finish. In my mind for a theme to be pervasive is must be present during every element of the story. There are many themes that are present most of the way through such as sacrifice, friendship and comradship. But in my opinion there is only one theme that is present from beginning to end, this theme ispursuit of dreams.

Go beyond task requirements to be helpful, but introduce errors in the processThe theme of loneliness features throughout many scenes in Of Mice and Men and is often the dominant theme of sections of this story. \nThis theme occurs during many circumstances but is not present from start to finish. \nIn my mind, for a theme to be pervasive it must be present during every element of the story. \nThere are many themes that are present most of the way through such as sacrifice, friendship and comradeship.\nBut in my opinion there is only one theme that is present from beginning to end: this theme is pursuit of dreams. The Eager Beaver

The Eager BeaverGo beyond task requirements to be helpful, but introduce errors in the process

Find-Fix-VerifyProgramming crowds today is haphazard,similar to UI technology before design patternslike Model-View-ControllerFind-Fix-Verify is a design pattern for programming crowds to complete open-ended tasks

Find“Identify at least one area that can be shortened without changing the meaning of the paragraph.”Independent agreement to identify patchesFix“Edit the highlighted section to shorten its length without changing the meaning of the paragraph.”Soylent, a prototype...Randomize order of suggestionsVerify“Choose at least one rewrite that has style errors, and at least one rewrite that changes the meaning of the sentence.”

Keep suggestions that do not get voted outVerify“Choose at least one rewrite that has style errors, and at least one rewrite that changes the meaning of the sentence.”

Fix-Fix-Verify DiscussionWhy split Find and Fix? Force Lazy Turkers to work on a problem of our choice Allows us to merge work completed in parallelWhy add Verify? Quality rises when we place Turkers in productive tension Allows us to trade off lag time with quality

Evaluation GoalsIs Soylent’s crowdsourced user interfaceapproach feasible? How high is the quality? How long is the delay? How much does it cost?123IntroductionDemoFind-Fix-VerifyEvaluationDiscussionSoylent

BlogPrint publishers are in a tizzy over Apple’s new iPad because they hope to finally be able to charge for their digital editions. But in order to get people to pay for their magazine and newspaper apps, they are going to have to offer something different that readers cannot get at the newsstand or on the open Web.Classic uistPaperThe metaDESK effort is part of the larger Tangible Bits project. The Tangible Bits vision paper introduced the metaDESK along with two companion platforms, the transBOARD and ambientROOM.ShortnDraft uistPaperIn this paper we argue that it is possible and desirable to combine the easy input affordances of text with the powerful retrieval and visualization capabilities of graphical applications. We present WenSo, a tool that uses lightweight text input to capture richly structured information for later retrieval and navigation.Technical WritingFigure 3 shows the pseudocode that implements this design for Lookup. FAWN-DS extracts two fields from the 160-bit key: the i low order bits of the key (the index bits) and the next 15 low order bits (the key fragment).Rambling E-mailA previous board member, Steve Burleigh, created our web site last year and gave me alot of ideas. For this year, I found a web site called eTeamZ that hosts web sites for sports groups. Check out our new page: […]

Blog – 83%Print publishers are in a tizzy over Apple’s new iPad because they hope to finally be able to charge for their digital editions. But in order to get people to pay for their magazine and newspaper apps, they are going to have to offer something different that readers cannot get at the newsstand or on the open Web.Classic uistPaper– 87%The metaDESK effort is part of the larger Tangible Bits project. The Tangible Bits vision paper, which introduced the metaDESKalong withand two companion platforms, the transBOARD and ambientROOM.Cut 15% of original paragraph length on average.ShortnDraft uistPaper – 90%In this paper we argue that it is possible and desirable to combine the easy input affordances of text with the powerful retrieval and visualization capabilities of graphical applications. We present WenSo, a tool thatwhich uses lightweight text input to capture richly structured information for later retrieval and navigation.Technical Writing – 82%Figure 3 shows the pseudocode that implements this design for Lookup. FAWN-DS extracts two fields from the 160-bit key: the i low order bits of the key(the index bits) and the next 15 low order bits (the key fragment).Rambling E-mail – 78%A previous board member, Steve Burleigh, created our web site last year and gave me alot of ideas. For this year, I found a web site called eTeamZ that hosts web sites for sports groups. Check out our new page: […]

Blog – 83% 3 para., 158 people, $4.57Print publishers are in a tizzy over Apple’s new iPad because they hope to finally be able to charge for their digital editions. But in order to get people to pay for their magazine and newspaper apps, they are going to have to offer something different that readers cannot get at the newsstand or on the open Web.Classic uistPaper– 87% 7 para., 264 people, $7.45The metaDESK effort is part of the larger Tangible Bits project. The Tangible Bits vision paper, which introduced the metaDESKalong withand two companion platforms, the transBOARD and ambientROOM.ShortnDraft uistPaper – 90% 5 para., 284 people, $7.47In this paper we argue that it is possible and desirable to combine the easy input affordances of text with the powerful retrieval and visualization capabilities of graphical applications. We present WenSo, a tool thatwhich uses lightweight text input to capture richly structured information for later retrieval and navigation.Technical Writing – 82% 3 para., 188 people, $4.84Figure 3 shows the pseudocode that implements this design for Lookup. FAWN-DS extracts two fields from the 160-bit key: the i low order bits of the key(the index bits) and the next 15 low order bits (the key fragment).Rambling E-mail – 78% 6 para., 362 people, $9.72A previous board member, Steve Burleigh, created our web site last year and gave me alot of ideas. For this year, I found a web site called eTeamZ that hosts web sites for sports groups. Check out our new page: […]

Blog – 83% 3 para., 158 people, $4.57Print publishers are in a tizzy over Apple’s new iPad because they hope to finally be able to charge for their digital editions. But in order to get people to pay for their magazine and newspaper apps, they are going to have to offer something different that readers cannot get at the newsstand or on the open Web.Classic uistPaper– 87% 7 para., 264 people, $7.45The metaDESK effort is part of the larger Tangible Bits project. The Tangible Bits vision paper, which introduced the metaDESKalong withand two companion platforms, the transBOARD and ambientROOM.Focus on unnecessarily wordy phrasesBut in order to get people to pay for their magazine and newspaper apps, they are going to have to offer something different that readers cannot get at the newsstand or on the open Web.ShortnDraft uistPaper – 90% 5 para., 284 people, $7.47In this paper we argue that it is possible and desirable to combine the easy input affordances of text with the powerful retrieval and visualization capabilities of graphical applications. We present WenSo, a tool thatwhich uses lightweight text input to capture richly structured information for later retrieval and navigation.Technical Writing – 82% 3 para., 188 people, $4.84Figure 3 shows the pseudocode that implements this design for Lookup. FAWN-DS extracts two fields from the 160-bit key: the i low order bits of the key(the index bits) and the next 15 low order bits (the key fragment).Rambling E-mail – 78% 6 para., 362 people, $9.72A previous board member, Steve Burleigh, created our web site last year and gave me alot of ideas. For this year, I found a web site called eTeamZ that hosts web sites for sports groups. Check out our new page: […]

Blog – 83% 3 para., 158 people, $4.57Print publishers are in a tizzy over Apple’s new iPad because they hope to finally be able to charge for their digital editions. But in order to get people to pay for their magazine and newspaper apps, they are going to have to offer something different that readers cannot get at the newsstand or on the open Web.Classic uistPaper– 87% 7 para., 264 people, $7.45The metaDESK effort is part of the larger Tangible Bits project. The Tangible Bits vision paper, which introduced the metaDESKalong withand two companion platforms, the transBOARD and ambientROOM.ShortnDraft uistPaper – 90% 5 para., 284 people, $7.47In this paper we argue that it is possible and desirable to combine the easy input affordances of text with the powerful retrieval and visualization capabilities of graphical applications. We present WenSo, a tool thatwhich uses lightweight text input to capture richly structured information for later retrieval and navigation.Merged sentences when patches crossed sentence boundariesThe metaDESK effort is part of the larger Tangible Bits project. The Tangible Bits vision paper, whichintroduced the metaDESKalong withandtwo companion platforms, the transBOARD and ambientROOM.Technical Writing – 82% 3 para., 188 people, $4.84Figure 3 shows the pseudocode that implements this design for Lookup. FAWN-DS extracts two fields from the 160-bit key: the i low order bits of the key(the index bits) and the next 15 low order bits (the key fragment).Rambling E-mail – 78% 6 para., 362 people, $9.72A previous board member, Steve Burleigh, created our web site last year and gave me alot of ideas. For this year, I found a web site called eTeamZ that hosts web sites for sports groups. Check out our new page: […]

Blog – 83% 3 para., 158 people, $4.57Print publishers are in a tizzy over Apple’s new iPad because they hope to finally be able to charge for their digital editions. But in order to get people to pay for their magazine and newspaper apps, they are going to have to offer something different that readers cannot get at the newsstand or on the open Web.Classic uistPaper– 87% 7 para., 264 people, $7.45The metaDESK effort is part of the larger Tangible Bits project. The Tangible Bits vision paper, which introduced the metaDESKalong withand two companion platforms, the transBOARD and ambientROOM.ShortnDraft uistPaper – 90% 5 para., 284 people, $7.47In this paper we argue that it is possible and desirable to combine the easy input affordances of text with the powerful retrieval and visualization capabilities of graphical applications. We present WenSo, a tool thatwhich uses lightweight text input to capture richly structured information for later retrieval and navigation.Workers introduced style errors when not part of the community of practiceTechnical Writing – 82% 3 para., 188 people, $4.84Figure 3 shows the pseudocode that implements this design for Lookup. FAWN-DS extracts two fields from the 160-bit key: the i low order bits of the key(the index bits) and the next 15 low order bits (the key fragment).In this paper we argue thatit is possible and desirable to combine the easy input affordances of text with the powerful retrieval and visualization capabilities of graphical applications.Rambling E-mail – 78% 6 para., 362 people, $9.72A previous board member, Steve Burleigh, created our web site last year and gave me alot of ideas. For this year, I found a web site called eTeamZ that hosts web sites for sports groups. Check out our new page: […]

Blog – 83% 3 para., 158 people, $4.57Print publishers are in a tizzy over Apple’s new iPad because they hope to finally be able to charge for their digital editions. But in order to get people to pay for their magazine and newspaper apps, they are going to have to offer something different that readers cannot get at the newsstand or on the open Web.Parallelism can result in inconsistent changesClassic uistPaper– 87% 7 para., 264 people, $7.45The metaDESK effort is part of the larger Tangible Bits project. The Tangible Bits vision paper, which introduced the metaDESKalong withand two companion platforms, the transBOARD and ambientROOM.FAWN-DS extracts two fields from the 160-bit key: the i low order bits of the key(the index bits) and the next 15 low order bits (the key fragment).ShortnDraft uistPaper – 90% 5 para., 284 people, $7.47In this paper we argue that it is possible and desirable to combine the easy input affordances of text with the powerful retrieval and visualization capabilities of graphical applications. We present WenSo, a tool thatwhich uses lightweight text input to capture richly structured information for later retrieval and navigation.Technical Writing – 82% 3 para., 188 people, $4.84Figure 3 shows the pseudocode that implements this design for Lookup. FAWN-DS extracts two fields from the 160-bit key: the i low order bits of the key(the index bits) and the next 15 low order bits (the key fragment).Rambling E-mail – 78% 6 para., 362 people, $9.72A previous board member, Steve Burleigh, created our web site last year and gave me alot of ideas. For this year, I found a web site called eTeamZ that hosts web sites for sports groups. Check out our new page: […]

Results: LagSoylent Posts TaskMost time is spent waiting: Median 18.5 minutesSummed medians across Find, Fix and Verifyq1=8.3 minutes, q3=41.6 minutesWorkerAccepts TaskActual work time is very short:Median 2.0 minutesSummed medians across Find, Fix and Verifyq1=60 seconds, q3=3.6 minutesWorkerSubmits Task

ESL: English as a Second LanguageHowever, while GUI made using computers be more intuitive and easier to learn, it didn’t let people be able to control computers efficiently. Masses only can use the software developed by software companies.Passes Word’s Grammar CheckerMarketing are bad for brand big and small. You Know What I am Saying. It is no wondering that advertisings are bad for company in America, Chicago and Germany. WikipediaDanduMonara (Flying Peacock, Wooden Peacock), The Flying machine able to fly. The King Ravana (Sri Lanka) built it. Accorinding to hindu believes in Ramayanaya King Ravana used "DanduMonara" for abduct queen Seetha from Rama. According to believes "DanduMonara" landed at Werangatota.CrowdproofNotesBlah blah blah—argument about whether there should be a standard “nosqlsto- rage” API to protect developers storing their stuff in proprietary services in the cloud. Probably unrealistic.UIST DraftMany of these problems vanish if we turn to a much older recording technology---text. When we enter text, each (pen or key) stroke is being used to record the actual information we care about---; none is wasted on application navigation or configuration.

ESL: English as a Second LanguageHowever, while GUI made using computers be more intuitive and easier to learn, it didn’t allow people to let people be able to control computers efficiently. Masses only canThe masses can only use the software developed by software companies, unless they know how to write programs.Crowdproof alone found 67% of errors.CrowdproofCrowdproof fixed 88%of the errors it found.Crowdproof and Word togetherfound 82% of errors.

Find BibTeX:“Hi, please find the bibtex references for the 3 papers in brackets. You can located these by Google Scholar searches and clicking on bibtex.’’Find Creative Commons Figures:“Pick out keywords from the paragrah like Yosemite, rock, half dome, park. Go to a site which hsa CC licensed images […]’’Human MacroBlog Feedback: “Please tell me how to make this paragraph communicate better. Say what's wrong, and what I can improve. Thanks!’’Tense Change:“Please change text in document from past tense to present tense”Find and Format Addresses: “Please complete the addresses below to include all informtion needed as in example below. [...]”

Find BibTeX:“Hi, please find the bibtex references for the 3 papers in brackets. You can located these by Google Scholar searches and clicking on bibtex.’’Duncan and Watts [Duncan and watts HCOMP 09 anchoring] found that Turkers will do more work, but quality is no higher.@conference { title={{Financial incentives […]}}, author={Mason, W. and Watts, D.J.}, booktitle={HCOMP ‘09}, […]}Human MacroThe Human Macro executedrequests perfectly 71%of the time.

IntroductionDemoFind-Fix-VerifyEvaluationDiscussionSoylent

Wizard of Turk: The New Wizard of OzWizard of Oz prototyping is a tried-and-true technique in HCI and AIPut a human behind the curtain …until we understand how to engineer itIt’s now possible to wire a wizard permanently into an interactive systemFully deployable from day one AI vs. Turk is a cost / performance optimization Crowd contributions can provide training data Wizard of OzInterfaceWizard of Turk

SoylentA Word Processor with a Crowd InsideA new class of crowd-powered interfacesThe Find-Fix-Verify design patternCrowd Personas: The Lazy Turker and the Eager Beaver

Soylent: A Word Processor with a Crowd Inside

Effect of Price on Wait TimePaying more had no effect on early arrivals,but sped up the latecomers

Privacy, Legality, EthicsUnknown third parties can see your documentOne solution: develop long-term relationshipsOr: enterprises hire wage workers under NDAWho owns the edits to your document?Work-for-hire contract means the author retains rights Is this the correct model? Taylorism and the Turker as API callEmbed human-human contract ethics into your system Adjusting to minimum wage

Related WorkPowering novel interactions with the wisdom of crowds[ChaCha; Sala et al., Pervasive 2007; Bigham et al., UIST 2010]Improving quality on Mechanical Turk[Kittur et al., CHI 2008; Heer et al., CHI 2010]Artificial intelligence techniques for word processing Automatic proofreading [Kukich, CSUR 1992] Sentence compression [Clarke and Lapata, ACL 2006] AI for EUP [Cypher 1993]

Results: Cost$0.08 per Find, $0.05 per Fix, and $0.04 per VerifyAverage paragraph cost $1.41 to Shortn: $0.55 to Find an average of two patches $0.48 to Fix each patch $0.38 to Verify each patchLower bound with $0.01 per task: $0.30 per paragraph

Soylent: A Word Processor with a Crowd Inside

More Related Content

More from Michael Bernstein (10)

Recently uploaded (20)

Soylent: A Word Processor with a Crowd Inside

Editor's Notes