Open Source Timing and Cost Analysis

Question

I want to extract important terms from the text and create a set of terms for a specific domain. Then I want to find out how these words are used in the text, positively or negatively.

Do you know any open source project that will help me solve these problems?

Edit:

Sample text:

"Although car is not comfortable, I like the design of it." 

From this text I want to extract something like this:

 design: positive comfort(able): negative 

Answer 1

To parse text and obtain the required parts of speech, there are many sets of tools

http://incubator.apache.org/opennlp/

http://www.nltk.org/

and etc.

Check out http://en.wikipedia.org/wiki/Sentiment_analysis for ideas on how words are used positively or negatively, if you mean the meaning. I don't know any solid platforms for this, but maybe you can tell us more about your problem for some ideas.

In the absence of the tools that will do this for you, you may find that getting the NP and its associated ADJs will suffice. You will also need the detection of negation. I used this ohnlp.sourceforge.net file (based on Apache UIMA) and it comes with a negation detection algorithm that is moderately decent.