This is only a Preview!

You must Publish this diary to make this visible to the public,
or click 'Edit Diary' to make further changes first.

Posting a Diary Entry

Daily Kos welcomes blog articles from readers, known as diaries. The Intro section to a diary should be about three paragraphs long, and is required. The body section is optional, as is the poll, which can have 1 to 15 choices. Descriptive tags are also required to help others find your diary by subject; please don't use "cute" tags.

When you're ready, scroll down below the tags and click Save & Preview. You can edit your diary after it's published by clicking Edit Diary. Polls cannot be edited once they are published.

If this is your first time creating a Diary since the Ajax upgrade, before you enter any text below, please press Ctrl-F5 and then hold down the Shift Key and press your browser's Reload button to refresh its cache with the new script files.


  1. One diary daily maximum.
  2. Substantive diaries only. If you don't have at least three solid, original paragraphs, you should probably post a comment in an Open Thread.
  3. No repetitive diaries. Take a moment to ensure your topic hasn't been blogged (you can search for Stories and Diaries that already cover this topic), though fresh original analysis is always welcome.
  4. Use the "Body" textbox if your diary entry is longer than three paragraphs.
  5. Any images in your posts must be hosted by an approved image hosting service (one of: imageshack.us, photobucket.com, flickr.com, smugmug.com, allyoucanupload.com, picturetrail.com, mac.com, webshots.com, editgrid.com).
  6. Copying and pasting entire copyrighted works is prohibited. If you do quote something, keep it brief, always provide a link to the original source, and use the <blockquote> tags to clearly identify the quoted material. Violating this rule is grounds for immediate banning.
  7. Be civil. Do not "call out" other users by name in diary titles. Do not use profanity in diary titles. Don't write diaries whose main purpose is to deliberately inflame.
For the complete list of DailyKos diary guidelines, please click here.

Please begin with an informative title:

I just found that little note and learned that our German HQ is interested in a story about the Truth Teller App in combination with the coverage of the State of the Union.

I thought our FP and other political writers can check how good the Truth Teller App really is and compete in the truthfinding live-blogging on Dailykos and challenge the results the Truth Teller App provides.  


You must enter an Intro for your Diary Entry between 300 and 1150 characters long (that's approximately 50-175 words without any html or formatting markup).

What is the Truith Teller App, you ask?

Washington Post Truth Teller app aims to fact check politicians in real time.

"We feed a video into our Truth Teller, it extracts the audio, it turns that audio into a transcript, then it takes that text, runs an algorithm and matches claims in that text to our database of facts and then returns back to the user whether this is true or false," says Cory Haik, the Washington Post's executive producer for digital news.
What the Washington Post had in mind is somewhat something like a lie detector service in real-time for its readers or viewers, said Cory Haik here:
Our solution is Truth Teller, which aims to fact check speeches in as close to real time as possible. Truth Teller is a prototype of a news application built by the Post with funding from Knight Foundation's Prototype Fund. The prototype, built in three months, is a big step toward real-time fact checking....

...We are effectively taking in video, converting the audio to text, matching that text to our database, and then displaying, in real time, what’s true and what’s false. The key to the project’s success is building an authoritative database - our goal is to identify falsehoods, not create more of them.

Technical Details:

We are transcribing videos using Microsoft Audio Video indexing service (MAVIS) technology. MAVIS is a Windows Azure application which uses Deep Neural Net (DNN) based speech recognition technology to convert audio signals into words. Using this service, we are extracting audio from videos and saving the information in our Lucene search index as a transcript. We are then looking for the facts in the transcription. Finding distinct phrases to match is difficult. Instead, we are focusing on patterns.

We are using approximate string matching, or a fuzzy string searching algorithm. We are implemented a modified version Rabin-Karp using Levenshtein distance algorithm. This will be modified to recognize paraphrasing and negative connotations in the future.

Now the question is how good is the WP database of facts ... may be the NY Times has the better database ... /ducking

If we just could use the Truth Teller App right now, live, in the John Brennan Hearing and see how much he tells the truth or not, that would be too good to be true, wouldn't it?


Extended (Optional)

Your Email has been sent.