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.
What is the Truith Teller App, you ask?
"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....Now the question is how good is the WP database of facts ... may be the NY Times has the better database ... /ducking
...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.
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?