nltk_tone_analyzer / README.md
kishanj97's picture
Update README.md
c8f1eb5 verified
metadata
language:
  - en
tags:
  - nltk
  - swntiment
  - tone
  - nlp

import nltk from nltk.sentiment import SentimentIntensityAnalyzer

Download NLTK resources (only need to run once)

nltk.download('vader_lexicon')

Sample text for sentiment analysis

with open("lks.txt", 'r') as file: fl = file.read()

contactId = fl.split("|")[0] transcript=fl.split("|")[1] transcript=transcript.replace("'",'')

Initialize the sentiment analyzer

sia = SentimentIntensityAnalyzer() print(transcript)

Analyze sentiment

sentiment_score = sia.polarity_scores(transcript)

Initialize dictionary to store tone counts

tones = { 'analytical': 0, 'anger': 0, 'confident': 0, 'fear': 0, 'joy': 0, 'sadness': 0, 'tentative': 0 }

Apply thresholds and count tones

if sentiment_score['compound'] >= 0.05: # Threshold for positive sentiment tones['joy'] += 1 elif sentiment_score['compound'] <= -0.05: # Threshold for negative sentiment tones['anger'] += 1 elif sentiment_score['neg'] >= 0.5: # Threshold for high negativity tones['sadness'] += 1 elif sentiment_score['pos'] <= 0.2: # Threshold for low positivity tones['fear'] += 1 elif sentiment_score['neu'] >= 0.5: # Threshold for high neutrality tones['tentative'] += 1 else: # Otherwise, consider it analytical or confident tones['analytical'] += 1 tones['confident'] += 1

Print tone counts

print("Tone Counts:", tones)

sample output

#Tone Counts: {'analytical': 0, 'anger': 0, 'confident': 0, 'fear': 0, 'joy': 1, 'sadness': 0, 'tentative': 0}