0

Hy, I am working on project that based on sentiment analysis for product rating. I have data set for good words and Negative words. When any user comment on website for product it will rate automatically out of 10 So i am confused with clustering technique and ago that solve my problem Plzzx Help Thanks in Advance.

Luqman
  • 1
  • 1

1 Answers1

1

You are basically asking us what would be best for you to use as a classifier for your program while we have to idea how is your data stored.

However, it seems you only have two classes, positive and negative. And you want to classify new data based on word analysis of the data.

I have worked earlier in such problem, I used Rocchio's TF-IDF algorithm for such classification. You give it a set of training data (negative and positive words) and it classifies what later comes to the system.

It is based on vector classification and cosine similarity distance measure.

For more information you can read this paper. You can find an example of how the method works (on very small data) here.

Note: the provided example is a section of a project I worked on.

Everyone
  • 1,751
  • 13
  • 36
  • yes i have two separate notepad files one for good words and other for negative words. I want to cluster them in c# that is if user write a comment product is very nice it will look for word in dataset and rate it according to their classification – Luqman Feb 06 '17 at 05:07
  • This is almost exactly what I worked with. Using C# and implementing the method I talked about. The paper attached describes how the TF-IDF vector based classification works. You will have a vector of weights for positive words and another one for negative words. When a new comment appears, the comment is processed and given a vector, so you have 3 vectors, positive, negative, new comment. If the new comment was closer to positive you consider it a positive comment and so on. – Everyone Feb 06 '17 at 05:12
  • is there pseudo code or full fledge algorithim that may help me to implementing step by step – Luqman Feb 06 '17 at 05:14
  • The paper describes everything you will need. I admit, this isn't the easiest thing to do. But it is not over complicated. I have a few examples if you need you can contact me – Everyone Feb 06 '17 at 05:16
  • Yeah why not please guide about that how can i contact you personally ? – Luqman Feb 06 '17 at 05:18
  • If you want, you can reach me by email – Everyone Feb 06 '17 at 05:26
  • please provide your email or whats app Number for more guidence – Luqman Feb 06 '17 at 05:33
  • @Luqman Please see the edit of the answer. I provided a simple example (6 pages description). Tell me if you have any other concerns – Everyone Feb 08 '17 at 00:47
  • @alfasin can you provide module for implementing this idea like in c# – Luqman Feb 08 '17 at 11:44
  • @Luqman Hmm, I implemented all of it in C# but it is kind of ad-hoc and honestly I wouldn't give my project away. The examples are clear you can use them as pseudo-code – Everyone Feb 09 '17 at 00:33
  • Thankyou so much it really works for me . – Luqman Feb 10 '17 at 05:00
  • @Luqman Glad I helped. If you're satisfied with the answer I would appreciate if you select it as the accepted answer :-) – Everyone Feb 11 '17 at 02:57