Product Review Monitoring with Sentiment Analysis
Scheduled workflow scrapes product reviews via Decodo, analyzes sentiment with Gemini AI, logs results to Sheets, and sends Telegram alerts.
What it does
You automatically track product review trends as the system scrapes your listed URLs with Decodo and analyzes sentiment using Gemini AI. New insights appear instantly in your Google Sheets log while Telegram alerts notify you immediately whenever fresh reviews are processed.
Step by step
- Configure the Google Sheets trigger to watch for new rows or specific cell updates.
- Set up the Decodo node with the target product URL and select HTML selectors for review text elements.
- Define the Telegram bot token and chat ID in environment variables for the alert step.
Where the LLM does the work
- Prompt Gemini to classify each review into positive, negative, or neutral sentiment categories.
- Instruct the model to generate a one-sentence summary of key complaints or praises from grouped reviews.
- Refine the output format to ensure JSON compatibility for downstream code processing.
Watch out for
Decodo may fail if the website structure changes, so add error handling to retry or log failures gracefully.
Gemini API calls can be slow and costly, so batch process reviews instead of calling it per individual comment.
HTML selectors often break due to dynamic content loading, so verify the scraped data contains actual text before sending to LLM.
Tools that fit
Google Gemini Chat Model LLM Perform sentiment analysis and summarization
The agent brief
Everything your agent needs, including the gotchas. Copy it and go.
You are helping me build the following AI agent workflow. ## Goal Product Review Monitoring with Sentiment Analysis: Scheduled workflow scrapes product reviews via Decodo, analyzes sentiment with Gemini AI, logs results to Sheets, and sends Telegram alerts. ## Specification - What it does: You automatically track product review trends as the system scrapes your listed URLs with Decodo and analyzes sentiment using Gemini AI. New insights appear instantly in your Google Sheets log while Telegram alerts notify you immediately whenever fresh reviews are processed. - Trigger: On a schedule (Scheduled · daily) - Autonomy: Fully hands-off - Expected setup effort: about an afternoon - Tools/services involved: - Google Sheets: Store product URLs and log results - Decodo: Scrape user reviews from URLs - Google Gemini Chat Model: Perform sentiment analysis and summarization - Telegram: Send alerts with review summaries ## Known pitfalls, handle each one explicitly in your implementation 1. Decodo may fail if the website structure changes, so add error handling to retry or log failures gracefully. 2. Gemini API calls can be slow and costly, so batch process reviews instead of calling it per individual comment. 3. HTML selectors often break due to dynamic content loading, so verify the scraped data contains actual text before sending to LLM. ## Reference implementation https://n8n.io/workflows/11632 (workflow template) Fetch and inspect this before building. If it matches my stack, adapt it; if not, rebuild the pattern with my tools. ## Process requirements 1. Before building: ask me which of the listed tools I actually use and what my platform is (n8n / Make / code / other). Do not assume. 2. Adapt the pattern to my answers; do not force the reference stack. 3. Address every pitfall above; tell me how you handled each. 4. Provide a test plan I can run before letting this touch real data. 5. Ask before any step that sends messages, modifies data, or spends money. Source: https://usecasesforagents.com/use-case/automated-product-review-monitoring-with-sentiment-analysis/ via usecasesforagents.com
Frequently asked questions
Can I use a different Spreadsheet than Google Sheets?
Yes. Google Sheets is only the example spreadsheet in this recipe. The same flow works with Airtable, Baserow and Excel. Swap the spreadsheet connection and keep the rest of the setup as written.
Want this running in your business?
This is what I do. I design and build AI agents like this one, and keep them running. If you want it set up for your team instead of doing it yourself, get in touch.
Who it's for
Also fits E-commerce Operator.