Sentiment Analysis on Facebook Comments

jaredpk1

I'm curious if anyone has experience using the python tiles (or anything else) to do sentiment analysis. Specifically I would like to monitor comments on our social media platforms, and I'd love to do it in Domo if possible.

ArborRose

I don't see any reason why you couldn't. You could use the Python tiles to create a custom model or leverage built-in libraries. Use Domo's social media connectors to pull comments or posts to Domo or call with API. Or consider using Domo's Jupyter Notebooks (Python).

Something like this

from vaderSentiment.vaderSentiment import SentimentIntensityAnalyzer

import pandas as pd



# Load the dataset

df = pd.DataFrame(input_data)



# Initialize VADER

analyzer = SentimentIntensityAnalyzer()



# Analyze sentiment

def analyze_sentiment(comment):

    scores = analyzer.polarity_scores(comment)

    return scores['compound']



# Apply sentiment analysis to comments

df['sentiment_score'] = df['comment'].apply(analyze_sentiment)



# Label sentiment as Positive, Neutral, or Negative

def label_sentiment(score):

    if score > 0.05:

        return 'Positive'

    elif score < -0.05:

        return 'Negative'

    else:

        return 'Neutral'


df['sentiment_label'] = df['sentiment_score'].apply(label_sentiment)


output_data = df

ArborRose

I don't see any reason why you couldn't. You could use the Python tiles to create a custom model or leverage built-in libraries. Use Domo's social media connectors to pull comments or posts to Domo or call with API. Or consider using Domo's Jupyter Notebooks (Python).

Something like this

from vaderSentiment.vaderSentiment import SentimentIntensityAnalyzer

import pandas as pd



# Load the dataset

df = pd.DataFrame(input_data)



# Initialize VADER

analyzer = SentimentIntensityAnalyzer()



# Analyze sentiment

def analyze_sentiment(comment):

    scores = analyzer.polarity_scores(comment)

    return scores['compound']



# Apply sentiment analysis to comments

df['sentiment_score'] = df['comment'].apply(analyze_sentiment)



# Label sentiment as Positive, Neutral, or Negative

def label_sentiment(score):

    if score > 0.05:

        return 'Positive'

    elif score < -0.05:

        return 'Negative'

    else:

        return 'Neutral'


df['sentiment_label'] = df['sentiment_score'].apply(label_sentiment)


output_data = df

jaredpk1

Thanks … that's very helpful. I have the comments pulled so I will play with this to see how it works. I may have a few follow-up questions (new to the Domo python tile), but I'll see where I get