Machine Learning Problem- Creating a Word Feature Vector in Octave
Posted: Wed Feb 17, 2016 2:58 pm
Hello,
I am a high-schooler with an internship at a college in my city. I hope to take the work done here to science fair eventually. I am currently working on a machine learning project where we hope to use unsupervised learning to cluster text among thousands of articles in our database to see if there are any relevant relationships among words in the data that would not be apparent otherwise. My instructions are to create a word feature vector of 0's and 1's based on whether the word corresponding to the index appears. To begin, I would just be testing this out with the titles of articles. I would like to write a script to do this if possible.
I have GNU Octave installed and would be using that to do this, and I am familiar with the concept, but I don't have any idea about how to actually implement this with code in Octave.
Any advice on how to go about doing this would be greatly appreciated!
I am a high-schooler with an internship at a college in my city. I hope to take the work done here to science fair eventually. I am currently working on a machine learning project where we hope to use unsupervised learning to cluster text among thousands of articles in our database to see if there are any relevant relationships among words in the data that would not be apparent otherwise. My instructions are to create a word feature vector of 0's and 1's based on whether the word corresponding to the index appears. To begin, I would just be testing this out with the titles of articles. I would like to write a script to do this if possible.
I have GNU Octave installed and would be using that to do this, and I am familiar with the concept, but I don't have any idea about how to actually implement this with code in Octave.
Any advice on how to go about doing this would be greatly appreciated!