
import pandas as pd
import seaborn as sns
import matplotlib.pyplot as plt
import nltk
from nltk.sentiment.vader import SentimentIntensityAnalyzer

import warnings 
warnings.filterwarnings("ignore")


reviews_df = pd.read_csv('Airline_Reviews.csv')
reviews_df.head()


reviews_df.info()

<class 'pandas.core.frame.DataFrame'>
RangeIndex: 23171 entries, 0 to 23170
Data columns (total 20 columns):
 #   Column                  Non-Null Count  Dtype  
---  ------                  --------------  -----  
 0   Unnamed: 0              23171 non-null  int64  
 1   Airline Name            23171 non-null  object 
 2   Overall_Rating          23171 non-null  object 
 3   Review_Title            23171 non-null  object 
 4   Review Date             23171 non-null  object 
 5   Verified                23171 non-null  bool   
 6   Review                  23171 non-null  object 
 7   Aircraft                7129 non-null   object 
 8   Type Of Traveller       19433 non-null  object 
 9   Seat Type               22075 non-null  object 
 10  Route                   19343 non-null  object 
 11  Date Flown              19417 non-null  object 
 12  Seat Comfort            19016 non-null  float64
 13  Cabin Staff Service     18911 non-null  float64
 14  Food & Beverages        14500 non-null  float64
 15  Ground Service          18378 non-null  float64
 16  Inflight Entertainment  10829 non-null  float64
 17  Wifi & Connectivity     5920 non-null   float64
 18  Value For Money         22105 non-null  float64
 19  Recommended             23171 non-null  object 
dtypes: bool(1), float64(7), int64(1), object(11)
memory usage: 3.4+ MB


nltk.download('vader_lexicon') # Download the VADER lexicon
sia = SentimentIntensityAnalyzer()

# Initialize lists to store sentiment labels and scores
sentiment_labels = []
sentiment_scores = []

[nltk_data] Downloading package vader_lexicon to
[nltk_data]     C:\Users\hp\AppData\Roaming\nltk_data...
[nltk_data]   Package vader_lexicon is already up-to-date!


# Run sentiment analysis on each review by loop
for i in range(len(reviews_df)):
    review = reviews_df['Review'][i]
    sentiment_score = sia.polarity_scores(review)['compound']
    sentiment_scores.append(sentiment_score)
    
    # Determine sentiment label based on sentiment score
    if sentiment_score > 0.05:
        sentiment_labels.append('Positive')
    elif sentiment_score < 0.05:
        sentiment_labels.append('Negative')
    else:
        sentiment_labels.append('Neutral')
        
# Create a new DataFrame with the sentiment analysis results
sentiment_df = pd.DataFrame({
    'Airline' : reviews_df['Airline Name'],
    'Review': reviews_df['Review'],
    'Sentiment_Label': sentiment_labels,
    'Sentiment_Score': sentiment_scores
})

print("Sentiment Analysis Results:")
print(sentiment_df.head(10))

Sentiment Analysis Results:
         Airline                                             Review  \
0    AB Aviation    Moroni to Moheli. Turned out to be a pretty ...   
1    AB Aviation   Moroni to Anjouan. It is a very small airline...   
2    AB Aviation    Anjouan to Dzaoudzi. A very small airline an...   
3  Adria Airways    Please do a favor yourself and do not fly wi...   
4  Adria Airways   Do not book a flight with this airline! My fr...   
5  Adria Airways    Had very bad experience with rerouted and ca...   
6  Adria Airways    Ljubljana to Zürich. Firstly, Ljubljana airp...   
7  Adria Airways    First of all, I am not complaining about a s...   
8  Adria Airways    Worst Airline ever! They combined two flight...   
9  Adria Airways   Ljubljana to Munich. The homebase airport of ...   

  Sentiment_Label  Sentiment_Score  
0        Positive           0.9192  
1        Negative          -0.9242  
2        Positive           0.7569  
3        Negative          -0.9600  
4        Negative          -0.1416  
5        Negative          -0.6106  
6        Negative          -0.9617  
7        Negative          -0.8216  
8        Negative          -0.2942  
9        Positive           0.8514


plt.figure(figsize=(10,150))

g = sns.stripplot(
    data=sentiment_df,
    x="Sentiment_Score", y="Airline", hue="Sentiment_Label",
    jitter=True, dodge=False, size=3)

g.set(xlabel="", ylabel="")

plt.legend(loc='upper left', bbox_to_anchor=(1, 1))
plt.show()

	Unnamed: 0	Airline Name	Overall_Rating	Review_Title	Review Date	Verified	Review	Aircraft	Type Of Traveller	Seat Type	Route	Date Flown	Seat Comfort	Cabin Staff Service	Food & Beverages	Ground Service	Inflight Entertainment	Wifi & Connectivity	Value For Money	Recommended
0	0	AB Aviation	9	"pretty decent airline"	11th November 2019	True	Moroni to Moheli. Turned out to be a pretty ...	NaN	Solo Leisure	Economy Class	Moroni to Moheli	November 2019	4.0	5.0	4.0	4.0	NaN	NaN	3.0	yes
1	1	AB Aviation	1	"Not a good airline"	25th June 2019	True	Moroni to Anjouan. It is a very small airline...	E120	Solo Leisure	Economy Class	Moroni to Anjouan	June 2019	2.0	2.0	1.0	1.0	NaN	NaN	2.0	no
2	2	AB Aviation	1	"flight was fortunately short"	25th June 2019	True	Anjouan to Dzaoudzi. A very small airline an...	Embraer E120	Solo Leisure	Economy Class	Anjouan to Dzaoudzi	June 2019	2.0	1.0	1.0	1.0	NaN	NaN	2.0	no
3	3	Adria Airways	1	"I will never fly again with Adria"	28th September 2019	False	Please do a favor yourself and do not fly wi...	NaN	Solo Leisure	Economy Class	Frankfurt to Pristina	September 2019	1.0	1.0	NaN	1.0	NaN	NaN	1.0	no
4	4	Adria Airways	1	"it ruined our last days of holidays"	24th September 2019	True	Do not book a flight with this airline! My fr...	NaN	Couple Leisure	Economy Class	Sofia to Amsterdam via Ljubljana	September 2019	1.0	1.0	1.0	1.0	1.0	1.0	1.0	no

Sentiment Polarity Analysis of Airline Reviews using NLTK