First of all, I should mention that I have a very basic knowledge of ML so I apologize if this question seems trivial or stupid.

I am working on a small personal project, basically an app that analyzes Facebook posts concerning movies and translates them into a rating (out of 100). The algorithm looks for keywords, the length of the post, etc.. to determine the individual rating, and then averages all the ratings among a user's FB friends to give the result. My question is, would I be able to drastically improve such algorithm by using ML or is it not worth it? If yes, what algorithms/techniques do you advise me to learn?

All help is appreciated!

  • 3
    $\begingroup$ (1) Do you have access to data which has "true" ratings for the movies for some users that have also written the same kinds of text that you are analysing? If so, how much of this data do you have? (2) Do you have any measure or test for your current algorithm such that you know how accurate it is? $\endgroup$ – Neil Slater Aug 19 '19 at 6:52

for this kind of ml training, you will need a ton of data first, at least in the thousands. If you have a bot program that fetches those data for you, AI is the way to go. I'm not sure how else you would do it though.

To train the nn you will need the inputs(the post) and the targets(the rating you want it to output). The targets could be anything you want, like the ratio of likes to views, etc.

There are tons of ML libraries out there and I recommend keras as it is easy to learn for beginners, hope it helps :)

| improve this answer | |

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy