How to Implement Sentiment Analysis on User Feedback in FlutterFlow

Go to console.cloud.google.com and select your project. In the search bar type 'Natural Language API' and click Enable. Next, go to APIs & Services → Credentials → Create Credentials → API Key. Copy the key. For production, restrict the key to the Natural Language API only by clicking Edit on the key and setting API restrictions. Store this key as a Firebase environment variable: in your terminal run 'firebase functions:config:set nlp.key=YOUR_API_KEY'. This keeps the key off the client and out of your codebase.

Create a new Cloud Function that triggers when a document is written to your feedback collection. It reads the comment text, calls the Natural Language API, extracts the score and magnitude, then writes those values back to the same Firestore document. This is a Firestore onWrite trigger — it fires automatically every time a feedback document is created or updated, so you never need to call it manually from your app. Deploy with 'firebase deploy --only functions'.

1// functions/index.js
2const functions = require('firebase-functions');
3const admin = require('firebase-admin');
4const axios = require('axios');
5
6admin.initializeApp();
7
8exports.analyzeFeedbackSentiment = functions.firestore
9  .document('feedback/{feedbackId}')
10  .onCreate(async (snap, context) => {
11    const data = snap.data();
12    const text = data.comment;
13    if (!text || text.trim().length === 0) return null;
14
15    const apiKey = functions.config().nlp.key;
16    const url = `https://language.googleapis.com/v1/documents:analyzeSentiment?key=${apiKey}`;
17
18    try {
19      const response = await axios.post(url, {
20        document: { type: 'PLAIN_TEXT', content: text },
21        encodingType: 'UTF8',
22      });
23
24      const sentiment = response.data.documentSentiment;
25      const score = sentiment.score;       // -1.0 to +1.0
26      const magnitude = sentiment.magnitude; // 0 to infinity
27
28      // Classify for easy filtering
29      let label = 'neutral';
30      if (score >= 0.25) label = 'positive';
31      if (score <= -0.25) label = 'negative';
32
33      await snap.ref.update({
34        sentiment_score: score,
35        sentiment_magnitude: magnitude,
36        sentiment_label: label,
37        analyzed_at: admin.firestore.FieldValue.serverTimestamp(),
38      });
39
40      console.log(`Feedback ${context.params.feedbackId}: ${label} (${score})`);
41      return null;
42    } catch (error) {
43      console.error('Sentiment analysis failed:', error.message);
44      return null;
45    }
46  });

In FlutterFlow, open your feedback page. Make sure it has a TextField for the comment and a Button to submit. In the Button's Action Flow, add a Firestore Create Document action targeting your 'feedback' collection. Map the TextField value to the 'comment' field. Also store the current user's UID (from Authenticated User → uid) and a timestamp (from Set from Variable → Current Time). You do NOT need to include sentiment fields — the Cloud Function populates those automatically after the document is created. Add a SnackBar action after the create action to show 'Thanks for your feedback!'.

Create a new page called 'Admin Dashboard' in FlutterFlow. Add a Backend Query at the page level that fetches all documents from the feedback collection, ordered by analyzed_at descending. Add three Count widgets showing the number of documents where sentiment_label equals 'positive', 'negative', and 'neutral' respectively — use Firestore Query conditions to filter. Add a Bar Chart widget: set the X axis to the submission date (grouped by day) and the Y axis to the average sentiment_score. Finally, add a ListView below the chart showing recent feedback cards with the comment text and a color-coded sentiment badge (green, red, neutral).

Extend your Cloud Function to send an alert email when the rolling negative sentiment ratio exceeds a threshold. After writing the sentiment data back to Firestore, query the last 50 feedback documents and calculate the percentage that are 'negative'. If it exceeds 30%, send an alert using the Firebase Transactional Email extension or a simple SendGrid API call. Add a cooldown check by storing the last alert time in a Firestore config document so you don't flood your inbox.

1// Add inside analyzeFeedbackSentiment, after the snap.ref.update() call:
2const db = admin.firestore();
3const recentDocs = await db.collection('feedback')
4  .orderBy('analyzed_at', 'desc')
5  .limit(50)
6  .get();
7
8const analyzed = recentDocs.docs.filter(d => d.data().sentiment_label);
9const negCount = analyzed.filter(d => d.data().sentiment_label === 'negative').length;
10const negRatio = negCount / analyzed.length;
11
12if (negRatio > 0.30) {
13  const configRef = db.doc('config/sentiment_alerts');
14  const config = await configRef.get();
15  const lastAlert = config.data()?.last_alert_at?.toMillis() || 0;
16  const oneHour = 60 * 60 * 1000;
17
18  if (Date.now() - lastAlert > oneHour) {
19    // Send alert via your preferred email service
20    console.warn(`ALERT: ${Math.round(negRatio * 100)}% negative sentiment in last 50 reviews`);
21    await configRef.set({ last_alert_at: admin.firestore.FieldValue.serverTimestamp() }, { merge: true });
22  }
23}