User analysis based on their facebook profile?

Question

I am pretty much sure that if you look carefully at any friend's timeline profile you can easily predict what going on in his/her life, Even you can write his/her entire life, you can also find out the hidden fact which he/she never told or updated directly but indirectly he/she shared n liked related thing which will help you to analyze his/her activity. Is it anyway possible to build an automated system which can read n analyze friends entire facebook profile, his/her shared stuff, likes, comments etc. and create a report which will expose his/her entire life facts including hidden one, using some AI or Machine learning concepts?

Hong

To some extent, but you're talking about a very complex system, since for example you'll need to deduce from a url that the user liked that it's (let's say) music related and is about a band. Also, you'll want to know what it meant that the user "liked" that page, what really did he like there? Another thing is that the data that facebook offer you is subjected to what the user grants you and you can get it only if he interacts with your app, you need to offer the user enough incentives to grant you all the data, which is not a simple thing to do. – Fjord

In addition, your AI will need to know the difference between caption/description and message data on a user profile, this can often blend and is added to all types of post, video, link, photo etc;. If you ever get your Annabot crawling, i will line up to test for you. :-) – Bogie

Also note that such a report will be a summary of many models. So, to get started, try to figure out what models you can obtain. This can be a model of user preferences, profession, communication style, etc. In fact, for most practical tasks these separate models will be enough. – Gilpin

saplo api is an api which can be used in text analytics and when i read this question then my gut instinct told me that this api can be used somewhere if we have to develop and intelligent system like this. so for stackoverflow i am pasting this link. may be it can help people [blog.saplo.com/category/api/] – Autarky

Answer 1

There's no system that will automatically be able to give content and understanding like you're looking for automatically. The human mind is able to infer a lot that computers simply can't understand. Also, you (generally) know some things about the people outside of Facebook (since you are friends with them) that fills in a lot of detail that the analysis system won't have.

The best thing you can do is to clearly define your problem and question that you're asking. There was a 'gaydar' project at MIT that was able to look at networks of students and generally correlate which ones are gay. For large groups you'll find it works overall, but for an individual person you're not going to be able to have great certainty.

Yet, to just ask the computer to 'find hidden information' won't work. You need to have a pretty solid model to work with. Overall, you're probably going to need a lot of data with confirmed facts to get started on testing that model as well (thousands of points needed). Also, with any social network you'll find that there is a lot of inaccurate/fake data on any given social network. People mis-list things all the time for various reasons (humor, etc) and this is going to throw off your models.

Tarratarradiddle