MOBA/aspectAnalysis.py at master · BEQUANTaSlov/MOBA · GitHub

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
import pandas as pd
import numpy as np
import nltk
from nltk.corpus import stopwords
from nltk.corpus import wordnet
from nltk.tokenize import word_tokenize, sent_tokenize
from nltk.stem.wordnet import WordNetLemmatizer
import stanfordnlp
import stanza


# Make sure you have downloaded the StanfordNLP English model and other essential tools using,
# stanfordnlp.download('en')
# nltk.download('stopwords')
# nltk.download('punkt')
# nltk.download('averaged_perceptron_tagger')

def aspect_sentiment_analysis(txt, stop_words, nlp):

    txt = txt.lower() # LowerCasing the given Text
    sentList = nltk.sent_tokenize(txt) # Splitting the text into sentences

    fcluster = []
    totalfeatureList = []
    finalcluster = []
    dic = {}

    for line in sentList:
        newtaggedList = []
        txt_list = nltk.word_tokenize(line) # Splitting up into words
        taggedList = nltk.pos_tag(txt_list) # Doing Part-of-Speech Tagging to each word

        newwordList = []
        flag = 0
        for i in range(0,len(taggedList)-1):
            if(taggedList[i][1]=="NN" and taggedList[i+1][1]=="NN"): # If two consecutive words are Nouns then they are joined together
                newwordList.append(taggedList[i][0]+taggedList[i+1][0])
                flag=1
            else:
                if(flag==1):
                    flag=0
                    continue
                newwordList.append(taggedList[i][0])
                if(i==len(taggedList)-2):
                    newwordList.append(taggedList[i+1][0])

        finaltxt = ' '.join(word for word in newwordList)
        new_txt_list = nltk.word_tokenize(finaltxt)
        wordsList = [w for w in new_txt_list if not w in stop_words]
        taggedList = nltk.pos_tag(wordsList)

        import stanza
        stanza.download('en') # download English model
        nlp = stanza.Pipeline('en') # initialize English neural pipeline

        doc = nlp(finaltxt) # Object of Stanford NLP Pipeleine

        # Getting the dependency relations betwwen the words
        dep_node = []
        for dep_edge in doc.sentences[0].dependencies:
            dep_node.append([dep_edge[2].text, dep_edge[0].id, dep_edge[1]])
        for i in range(0, len(dep_node)):
            if (int(dep_node[i][1]) != 0):
                dep_node[i][1] = newwordList[(int(dep_node[i][1]) - 1)]

        print(dep_node)
        # Coverted it into appropriate format

        featureList = []
        categories = []
        for i in taggedList:
            if(i[1]=='JJ' or i[1]=='NN' or i[1]=='JJR' or i[1]=='NNS' or i[1]=='RB'):
                featureList.append(list(i)) # For features for each sentence
                totalfeatureList.append(list(i)) # Stores the features of all the sentences in the text
                categories.append(i[0])

        for i in featureList:
            filist = []
            for j in dep_node:
                if((j[0]==i[0] or j[1]==i[0]) and (j[2] in ["nsubj", "acl:relcl", "obj", "dobj", "agent", "advmod", "amod", "neg", "prep_of", "acomp", "xcomp", "compound"])):
                    if(j[0]==i[0]):
                        filist.append(j[1])
                    else:
                        filist.append(j[0])
            fcluster.append([i[0], filist])

    for i in totalfeatureList:
        dic[i[0]] = i[1]

    for i in fcluster:
        if(dic[i[0]]=="NN"):
            finalcluster.append(i)

    return(finalcluster)
'''
nlp = stanfordnlp.Pipeline()
stop_words = set(stopwords.words('english'))
txt = "The Sound Quality is great but the battery life is very bad."

print(aspect_sentiment_analysis(txt, stop_words, nlp))
'''