After some experimentation with simple machine learning I realize there are Machine Learning services out there and I need one to help match two closely related news. It is much like the popular WordPress "Related Posts" feature.
Any one in the house should help.

The task is I need to cluster news coverage from different news outlet from media houses. I still need it.

I can achieve this with python and libraries like sk-learn and scipy

demolinton4comi:
I can achieve this with python and libraries like sk-learn and scipy

How will you achieve it? demolinton4comi? What approach.

If am to use sklearn I will use the following steps.
-data preprocessing
-create a vector dataset from the sentence
- transform it to tf-idf format
-compute cosine similarities.
Also son clustering algorithm like k mean will also be good to be used as post processing.... Pls note the higher the length of sentence the lesser the accuracy of the result.... So if u want more accurate result the preprocessing section u have to be worked on......,...

@demolinton4comi
What of the sentences in each news are much. I have the full news.

I Neva said its simple....... Its just a procedural step u can take to achieve this.. Am not really use to this forum that's for my late response for further assistance u can reach me on WhatsApp via 08144737987.......... Even if it is sentence or textbook that procedure should do the trick

Nice thread.