5
$\begingroup$

I am doing sentiment analysis on given documents. My goal is to find out the closest or surrounding adjective words with respect to the target phrase in my sentences. I do have an idea how to extract surrounding words with respect to target phrases. But how do I find out relatively close or closest adjective or NNP or VBN or other POS tag with respect to target phrase ?

Here is the sketch idea of how I may get surrounding words with respect to my target phrase.

sentence_List = {
    "Obviously one of the most important features of any computer is the human interface.", 
    "Good for everyday computing and web browsing.",
    "My problem was with DELL Customer Service", 
    "I play a lot of casual games online[comma] and the touchpad is very responsive"
}

target_phraseList = {
    "human interface",
    "everyday computing",
    "DELL Customer Service",
    "touchpad"
}

Note that my original dataset was given as DataFrame where the list of the sentences and respective target phrases were given. Here I just simulated data as follows:

import pandas as pd
df=pd.Series(sentence_List, target_phraseList)
df=pd.DataFrame(df)

Here, I tokenize the sentence as follow:

from nltk.tokenize import word_tokenize
tokenized_sents = [word_tokenize(i) for i in sentence_List]
tokenized=[i for i in tokenized_sents]

Then I try to find out surrounding words with respect to my target phrases by using this loot at here. However, I want to find out relatively closer or closest adjective, or verbs or VBN with respect to my target phrase.

How can I make this happen? Any idea to get this done? Thanks

$\endgroup$
  • $\begingroup$ Take a look at spacy, they have models already trained to POS tag a text. $\endgroup$ – skd Nov 20 '18 at 17:13
1
$\begingroup$

POS-tagging consist of qualifying words by attaching a Part-Of-Speech to it. Part-Of-Speech is a tag that indicates the role of a word in a sentence (e.g. a noun, a transitive verb, a comparative adjective, etc.). You need this to know if a word is an adjective, and it is easily done with the nltk package you are using [source]:

>> nltk.pos_tag("The grand jury")
>> ('The', 'AT'), ('grand', 'JJ'), ('jury', 'NN')

Here, JJ means "Adjective" and "NN" means "Common Noun".

In your case, you are interested in neighbors adjectives. Does that mean "the closest adjective" in the sentence ? Or adjectives within a radius of the target, if any? Depending on the definition, the way to do it differs.

For adjectives within a radius, as you have already selected words within a radius using the snippet you mentioned, you can POS-tag them and then select only those with a tag that indicates an adjective tag.

>> adjective_tags = ["JJ", "JJR", "JJS"]
>> close_adjectives_list = [a[0] for a in nltk.pos_tag(" ".join(close_words_list)) if a[1] in adjective_tags ]

You can look at this answer that list most of existing POS-tags.

$\endgroup$

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Not the answer you're looking for? Browse other questions tagged or ask your own question.