Reputation: 2122
I'm planning a Social Network with an Artificial Intelligence . that means that the SN will take the conversations (in english) .. and analyse them in order to extract the general opinion about a subject. This helps to collect information and build statistics, which will be sent then to the appropriate user. My question is : how to organize words and grammatical rules in a database, in order to help the social network extracting a general opinion from a conversation (agree, disagree..etc)! thank you.
Upvotes: 1
Views: 996
Reputation: 5358
its very challengning task to extract text that reflects real opnions of people because machine learning is still not advanced in this area, take a look at the following example: your program finds this sentence on some SN website: "I made her duck"
what are possible options that your program will infer:
1-i cooked a duck for her
2-i "magically" transformed her into a duck"
3-i took her duck and created it.
and many other
so its really challenge. I suggest to take a look at NLP(natural language processing) which covers this area you're interested in
Upvotes: 1
Reputation: 13727
Could you plug Wolfram Alpha (http://www.wolframalpha.com/about.html) into your site? That would save probably a LOT of work.
Upvotes: 1