Pentametron Reveals Unintended Poetry of Twitter Users

That sounds like what happens with poets and collected culture now--a poet looking to create a poem searches their memory for experience, chooses a form, and after some revisions produces a work. That work is then shopped around, sometimes in formal ways like a publisher, or informal through friends, and through time civilization filters and canonized certain poems, forever adding to, updating, and removing works from the list.

It seems possible, though certainly not easy, to mechanize some or all of that.

You want every possible sonnet? OK: http://wry.me/sonnetron

(slight exaggeration, yes.)

This reminds me of the Roald Dahl short story The Great Automatic Grammatizator, which, although dated, examines the possible consequences of automatically generating literature.

I also think of the sci-fi short story Melancholy Elephants by Spider Robinson, which examines how perpetual copyright would negatively impact music (there are only so many novel melodies that are pleasant to listen to): http://www.baen.com/chapters/W200011/0671319744___1.htm

Here's some pythonesque pseudo-code that might do it:

    for tweet in twitter_api.latest_tweets():
        phonetic_tweet = convert_tweet_to_phonemes(tweet)
        
        if is_iambic(phonetic_tweet):
            end_rhymes = extract_end_rhymes(phonetic_tweet)
            db.insert_iambic_tweet(tweet, end_rhymes)
            
            for end_rhyme in end_rhymes:
                rhyming_tweets = db.select_rhyming_tweets(end_rhyme)
                if rhyming_tweets:
                    rhyming_tweet = random.choice(rhyming_tweets)
                    return [tweet, rhyming_tweet]

There are several open source word lists out there that make this feasible.

I also wrote a filter over Twitter for iambic pentameter once, and had a friend write a web frontend to it. Here's my (messy) code; http://glozer.net/ wrote the frontend in Erlang but AFAIK never released it.

https://github.com/darius/versecop

Pentametron is cooler. I did try filtering for rhymes too, but there wasn't enough data in the free feed, at least back then.

I read somewhere that it uses the cmu pronouncing dictionary which would give it both the meter and rhyme it needs (http://www.speech.cs.cmu.edu/cgi-bin/cmudict)

I don't know if this one does all those things, but it's been featured here:

Show HN: An IDE for poets (http://tranquillpoet.com) http://news.ycombinator.com/item?id=4775886