Python - Splitting positive/negative/neutral/ feedback sentiment score from Vader into separate columns and adding it to data set

user_14095566 0
Viewed 832

I'm trying to determine the sentiment score for customer feedback using VADER in python. The simple code below is running perfectly for individual feedback and returning a dictionary of negative, neutral, positive and compound score.

Code:

from vaderSentiment.vaderSentiment import SentimentIntensityAnalyzer


feedback = "Food was very good"
vader = SentimentIntensityAnalyzer()
sentiment = vader.polarity_scores(feedback)

print(sentiment)

result: {'neg': 0.0, 'neu': 0.484, 'pos': 0.516, 'compound': 0.4927}

Now, I have a spreadsheet of 4k+ customer feedback. What I'm trying to do is to iterate through every feedback and add 4 new col as Negative_Score, Neutral_Score, Positive_Score and Compound_Score. I've written following code which is not giving desired result. Getting same score for every row. Any help will be appreciated.

Code:

    import os.path
    from vaderSentiment.vaderSentiment import SentimentIntensityAnalyzer
    import pandas as pd

    data = pd.read_excel(r"C:\...\sample_feedback.xlsx") 
    #Sample_feedback.xlsx has two col customer and feedbacktext
    vader = SentimentIntensityAnalyzer()
    data["Negative_Score"] = vader.polarity_scores(data["feedbacktext"]).get("neg")
    data
vader pandas xlsx sentiment-analysis python
1 Answers

We can achieve this using lambda. It is better than iterating through the data frame rows. I have written a method vader_scores the sole function is to return the respectivite polarity score (pos/neg/neu/compound) from the feedback text.

The main reason your code returned the same polarity score for all rows was that you had used data["feedbacktext"] alone, which took the entire column and returned the resultant value for it. What I have done is, have picked the data["feedbacktext"] from every row using the index of the row and have populated its cell in Negative_Score , Neutral_Score, Positive_Score, and Compound_Score columns.

The sample data I had used was :

enter image description here

This is my code:

import os.path
from vaderSentiment.vaderSentiment import SentimentIntensityAnalyzer
import pandas as pd

def vader_scores(feedbacktext, category):
    return vader.polarity_scores(feedbacktext).get(category)

data = pd.read_excel(r"sample_feedback.xls") 
# print(data)
#Sample_feedback.xlsx has two col customer and feedbacktext
vader = SentimentIntensityAnalyzer()

data["Negative_Score"] = data.apply(lambda row : vader_scores(data["feedbacktext"][row.name], "neg"),axis=1)
data["Neutral_Score"] = data.apply(lambda row : vader_scores(data["feedbacktext"][row.name], "neu"),axis=1)
data["Positive_Score"] = data.apply(lambda row : vader_scores(data["feedbacktext"][row.name], "pos"),axis=1)
data["Compound_Score"] = data.apply(lambda row : vader_scores(data["feedbacktext"][row.name], "compound"),axis=1)
data

And the OUTPUT is:

enter image description here

user_72451450
Related