Friday, September 5, 2008

SezHoo and WikiSym 2008

I'm proud to announce the release of SezHoo! It's a tool we created at MITRE to help establish reputations for authors in wiki sites... specifically those run on MediaWiki (the same software that runs Wikipedia).

The way that SezHoo works is that it goes through a wiki article's history and tracks the authorship of each word in the article. We use a pretty popular technique in text analysis called shingling to help us out.

For each revision of an article, we break it up into shingles. We're using shingles that are 6 words long, so each word will have 6 shingles associated with it. We credit authorship of the word to the author of the earliest shingle.

This allows us to add some information to a MediaWiki installation:

Pages
We show the authors of a page, and the percentages at which they have contributed. We also offer this information at the section level.

The information we compute is better than doing diffs with a standard MediaWiki install. Diffs are line ending based, so changing a word in a paragraph that has a single line ending can make it difficult to determine who wrote the paragraph. In addition, since we are looking for authorship of a word across all revisions at once (as opposed to a revision vs. revision comparison with a diff), this technique is immune to copying and pasting of text and reversion of vandalism.

Authors
We create a reputation for authors with 3 dimensions: quantity, quality and value. For all metrics, we assign a 5 star rating. The way this is done is by computing a raw score for all authors and then ranking them. Authors in the top 20% have a 5-star rating in that dimension.

For quantity, we simply calculate the number of word contributed by each author. This includes words that may no longer be in the current revision of the article. Value takes the percentage authorship of a page, and multiplies that by the number of page views (it's valuable if it's being read).

Quality is a lot more tricky. We assume that wiki articles are a Darwinian environment. That is, quality text will "survive" in that as the article is edited, other authors will leave the text alone. Poor quality text will be "killed" or deleted by other authors. We determine quality by looking at the percentage of text that is expected to be alive for an author after 8 revisions (you can change 8 to whatever you like, but it works well for our internal wiki). To calculate the percentage alive after 8 revisions, we used a Kaplan-Meier estimate. This was necessary due to the fact that authors will have phrases which are "alive" (they are in the current version of an article). So if a word has survived 3 edits and is in the current version of an article, when calculating survival probabilities you don't want to say that it "died" at 3 revisions, but you don't want to lose the data either. Kaplan-Meier handles that for us.

In the end, you get a 5-star rating for each author in the dimensions of quantity, quality and value.



I'll be presenting this work at WikiSym 2008. We're doing some other interesting stuff which we haven't rolled into SezHoo yet, so it's worth coming to my talk even if you've read this blog post.

35 comments:

mirnarsmith said...

US day money enhancements at intervals Il possesses varied home mortgage alternatives just to be smart equally as, day money enhancements, Pay day advance else to Size money loans, in conjunction with auto title loans corona automotive Strategy money loans. the public target supporting you opt on to shop for for the right home mortgage product and services that may assist you to satisfy your individual economical needs.

foride88 said...

Check that you aces an assention arrangement that allows you to assert with your writer. There are bottomless associations that are putting exchanging this organization, yet there are also bounteous who don't activity such an irregularity to its custom. These associations consideration to be ignored for 2 reasons. custom essay writing services

Unknown said...

It is advisable to find the get in touch with target and get in touch with figures pertaining to easy transmission functions. It is important to assemble adequate data on websites, seeing that this will be a key determinant should they could match ones economic requirements within your preferred time period.car title loans montgomery

marko said...

As disappointed a borrower could get to be a result of these brought down figures, they need to advise themselves that these advances request a quick result. Moderateness is a tremendous consider regardless of whether the credit will be effective. payday loans

marko said...

However, now and again it may lead you to the wrong hands and in this manner, it is prudent to be careful before you seek a loan. Accumulate all data about the bank organization. Be mindful of the considerable number of conditions and interest rates about the advance. cash advance corona

Unknown said...

In the event that you are one of numerous focused on borrowers the nation over who experience the ill effects of terrible credit and are considering how to clean up your credit report quick then you have to peruse this article. It covers the fundamental idea of credit repair that will help you clear lapses from your report. chicago auto title loans online

marko said...

Abstain from purchasing utilized autos from purchase here-pay-here auto parts to get away from their higher interest rates and low quality of utilized autos. Additionally since they don't report the arrangement to the credit agencies it won't help in credit repair. Rather, choose banks that charge lower premium rate than these auto parts or take the advance from awful credit utilized auto advance moneylenders having notoriety for offering advance at reasonable rate of premium. cash advances

Unknown said...

The bread-and-butter business has awfully planned money accompanying affairs to bond you out and for the same; you can accede profiting bike advances Payday Loans San-diego

marko said...

You need to comprehend that these sorts of advances are constantly proposed to help you as an awful credit account holder and you ought to receive the greatest advantage in return. Find out about how to arrange with your merchant and get the most alluring interest rate and installment plan. check cashing in fresno ca

Unknown said...


Right when a borrower approaches the prompting connection, the credit is kept up in the wake of making some vital measures in a matter of seconds record as a purchaser of the borrower, and whether he has a sensible title to the auto.
auto title loans chicago

MUSA77 said...

There are assorted affirmation to acclaim auto costs organizations online today that absorb cogent time in giving car appellation advances and you'll ascertain these organizations action abundant choices on the area that they alike with a ample lot of the better auto annual organizations angular over North America and alike Canada. Keep in apperception an accomplished borrower is a adeptness borrower, acceptable fortunes to you.Cash Advance San-diego

Unknown said...


Thusly, there will be no wonders concerning paying back your credit without irritates. Remember that distinctive people using vehicle title credits are doing this as a last resort or as a transient response for getting smart cash, and you absolutely would bolster not to get included with any budgetary drive proficient who could manhandle your money related condition. You should reliably chase down the relationship of specific experts for real, record and assessment course before you sign anything.
Payday Loans

Unknown said...


We are one alongside the other about giving exact changed works with yearly to your bike crediting necessities, enquiries for a dynamic bike money abettor can beat 30 - 50 calls an acknowledgment conceivably more. In any case, be correct we likewise get paid from the bike's administering move, this is the best point part up your bike starting as of late upkeep rate!
auto title loans

JON said...

For lively early projection of beginning now you see to continue running with online house you confirmation accomplishment a basal online machine appearance on moneylender's armpit and a brief while later that, stand it. In the deathwatch of aggregate your typical data, the banknote is exchanged to you're sanctioning change best right 24 hours of use. Car Title Loans Chicago

Unknown said...

The use of auto as security is not constrained to title credits itself. Different moneylenders see the vehicles as security to back the credit reimbursement. Regardless, home gages remarkable in the favored once-over of securities. Payday Loans San-diego

Unknown said...

One thing that I did was to change into a bit for payday advance affiliations so that I could get paid from unmistakable individuals getting payday credits. A few individuals are fundamentally going to get them so there is no motivation driving why you shouldn't get paid from the procedure that made you pay to such an extent. Cash Advance

Unknown said...

One thing to survey is that you never need to take a gander at all of your assignments rapidly as you will feel the need to complete every one of them and feel that there's lacking time. Something else to consider is that every endeavor will have specific criteria and thusly you have to set aside an ideal opportunity to ingest and perceive what it is you have to do. car title loans near me chicago

Unknown said...

Aback you about-face jobs you may access your assets but there may be a acclimation aeon depending on the dates of the pay in your old job adjoin your new job. This can be abashing and may account your debt claim plan to go off kilter.
payday loans

Unknown said...

Despite the abject bulk of absorption absolute at an all time of low of 5%, acclaim agenda companies are boring accretion absorption rates; with new rules actuality imposed on the industry, aimed at giving consumers a bigger deal, the affairs are absorption ante will abide upwards. Basically if consumers are accepting a bigger deal, it agency the acclaim agenda companies will accomplish beneath money than they would like and accordingly attending to accomplish up the aberration through an admission in absorption rates.
payday loans corona

Unknown said...

There are several important factors to accede aback chief which blazon of accommodation you need. Do you allegation a ample amount? What is your acclaim history? Aback will you be able to pay aback the loan? Let's attending at a few key credibility that can advice you adjudge if you if you should administer for a coffer accommodation or a payday loan.
cash advance

Unknown said...


Most lenders will be assured you to accord the accommodation on your abutting payday but some may action added claim options that you should be acquainted of in the accident of an emergency. Accumulate these options in apperception back allotment a payday accommodation lender as well.
check cashing in fresno

Unknown said...

Once the loan is approved, the funds will be scheduled to transfer into the customer's account. The customer will be notified of the date in which the loan will need to be paid in full. In the event that the customer is unable to pay off the payday loan debt on the agreed upon date, "extensions" can be requested. These extensions usually have a fee associated with them.
Cash Advance Corona

Justin said...

Utilize your own rent as a manual for figure the tax reductions of San Diego townhouses or home. Possession for the most part gives you the chance to make a home loan installment, including assessments and protection, around 33% bigger than your present rent without changing your way of life. cash advance chicago

Justin said...

Applying for advance alteration is not that confused. You can do it without anyone else's help. The procedure is entirely straightforward: Find out on the off chance that you are qualified and on the off chance that you are, round out the best possible structures and submit them to your bank. On the off chance that you do it effectively, the bank can't turn you down. www.usacheckcashingstore.com/san-diego

Justin said...

Alte le misure di L-arginina sono state dette per rinvigorire la creazione bodys di gastrina, un ormone che espansioni stomaco corrosivo in modo che possa avere sintomi non sicuri sulla remota possibilità che si verificano gli effetti negativi di ulcere gastriche e per gli uomini che assumono farmaci che sono brutale sullo stomaco. erezione rimedi naturali

Justin said...

Nel caso ve lo stiate chiedendo il lungo elenco è stato ideato da una giuria di cinque uomini presieduto da Clive Lloyd, presidente del comitato di cricket ICC inclusi gli ex giocatori internazionali Angus Fraser, Matthew Hayden, Ravi Shastri e Duncan Fletcher e la cerimonia di premiazione sarà tenutosi a Bangalore il 6 ottobre Per la cronaca credo che Shane Watson il miglior marcatore di esecuzione in quel periodo con 2497 piste e 79 wicket a 22.64 DOVREBBE essere incoronato Cricketer dell'anno. la candidatura in inglese per berlino

marko said...

L'anno scorso abbiamo perso la nostra casa in un incendio. E 'stata una perdita terribile perché la proprietà era sotto assicurato. Mia moglie e alcuni dei miei amici mi interrogato sul motivo per cui questo disastro dovesse accadere a me, una persona positiva. http://www.disfunzione-erettile.org

marko said...

L'inglese è la lingua più parlata in tutto il mondo e può aiutare a colmare il divario di comunicazione tra persone di diversa countries.Today, tutti vogliono essere in grado di fare molto meglio di altri e, come tale, inglese in grado di fornire questo per loro. scrivere il curriculum vitae inglese senza errori

Paulo said...

Examined most of the terms and conditions by and large before you sign the development. Yes, you require the money, yet you need to know correctly what you are promising to do after you get it. check cashing san-diego

Paulo said...

Whether online or some other way, getting individual advance endorsement in spite of awful credit is more conceivable on the off chance that we look towards elective sources. We look a three of them. cash advance oceanside

Paulo said...

In circumstances where there are openings in the information, the moneylender will make a made summary that will be sent to you for satisfaction. This methodology is known as the "paper snowstorm", which is as drawing in as it sounds. The more grounded your development application package, the more impossible you should atmosphere such a whirlwind. Payday Loans Chicago

Robbert said...

Utilized autos are astonishing other options to purchasing new in light of the fact that it permits you to consider your fantasy autos without considering their off the industrial facility line cost. It is assessed that in the initial six months of being produced an auto, contingent upon the make and model, will lose somewhere around thirty and 50% of its esteem. Check Cashing

Robbert said...

Giving precise information with regards to specifying the quantity of miles to work, making installments by means of electronic store exchange (EFT) are different approaches to diminish premium effortlessly. On the off chance that you are a high hazard person who discovers trouble in getting auto protection in the typical course, state protection that gives essential scope could turn out to be an alternative. payday loans chula-vista

Robbert said...

Anything of significant worth, for example, your home, any land you may possess, or even the auto you need to purchase can be security. You can profit by a lower financing cost with a secured automobile advance, yet you likewise risk losing the insurance property on the off chance that you miss re-installments on the advance. check cashing

Paulo said...

A trader loan offered suing your charge card incomes is speedier to fit the bill for. We should audit the distinctions in the application procedure to acknowledge why. car title loans chicago