|
|
|
|
|
|
by examancer
4874 days ago
|
|
|
I am not sure if this site provides an accurate aggregate view of public opinion on movies, but if it does then I have no desire to know what the public likes. I also don't know how this is better than other "what does everyone think?" ratings available on IMDB or rotten tomatoes. The real beauty of all the social data now available is that a service like this could theoretically provide ratings based on the sentiment of people who's opinions I follow or who are have similar tastes to me. I don't care how much the average person loves Pitch Perfect, its just not something want on my list of potential movies. If I were matched through my social iterations to people who's ratings are relevant that would likely be obvious. I love seeing new software in this space and I hope you develop it further, but you're going to need to dive much deeper into the social data available if you want to really make a disruption. |
|
|
The (simplified) idea for recommending movies was:
1. Crawl a torrent site (say, the pirate bay) for as many torrents you can find. Extract the title, description, magnet link and category for each torrent. 2. Use the DHT network to find out which IP addresses are downloading what torrents 3. Use these (torrent, ip) tuples to build a recommendation based on "People who download X also download Y"
This way you can try to find movies that are liked (or actually, downloaded) by people with similar taste to you. The quality of this recommender is quite impressive in my opinion.
Email me at arno at vanlumig dot com if you want to see the proof of concept, I won't post a link here because the performance is quite bad and I'm sure the server won't be able to handle any significant load.
I will make the data (torrent metadata and data about who downloaded what) available as soon as I've anonymised the IP addresses, also mail me if you're interested in that data.