Translator Customer Review Aggregator

Overview

This flow gives Marketing and Operations a single, English-normalized view of global customer sentiment. On a schedule it pulls reviews from one or more RSS/HTTP feeds (app stores, review sites), translates each review to English with Microsoft Translator V3 (auto-detecting the source language), scores sentiment with an in-flow keyword model, stores every review in a Dataverse table, and posts only the negative or notable ones into a Teams marketing channel. Reviews arrive in many languages across many sites; aggregating and normalizing them to English makes global sentiment readable and surfaces the reviews that need a response, without drowning the channel in routine 5-star feedback.

Use Case

A product/marketing team monitors customer reviews across regions and wants them centralized, translated to a common language, sentiment-scored, persisted for trend reporting, and the important ones surfaced in Teams in near-real-time. The flow is idempotent: it de-duplicates on the review feed id, so re-runs never re-post or duplicate a stored review.

Flow Architecture

Environment Variables

Connectors & Connections

Connector	API name	Actions used
RSS	shared_rss	ListFeedItems
Microsoft Translator	shared_microsofttranslatorv	Translate
Microsoft Dataverse	shared_commondataserviceforapps	ListRecords CreateRecord
Microsoft Teams	shared_teams	PostMessageToConversation

Customization Guide

Almost every realistic variant of this flow can be implemented by changing environment variable values. A few cases require small edits inside the flow definition — those are called out explicitly below.

Feeds

Set flowlibs_RSSFeedURLs to any RSS/HTTP review feeds. For sites without RSS, swap List Feed Items for an HTTP call to the reviews API and adjust field mappings.

Cadence

Edit the Every 6 Hours recurrence (e.g. hourly, daily) to match review volume.

Sentiment tuning

Extend the negative/notable keyword lists, add a positive list, or insert an Azure AI Language DetectSentiment / Azure OpenAI action for richer scoring.

Language

Change flowlibs_ReviewTargetLanguage to localize the normalized output (e.g. fr, de).

Routing

Point the Teams group/channel env vars at the destination channel, or add an Outlook SendEmailV2 to email a manager in parallel.

Trend reporting

Build a Power BI report over the flowlibs_customerreview table for sentiment-by-region/source trends.

Key Expressions

The flow is intentionally light on Power Fx / WDL gymnastics — the heaviest expressions are the branch-name concatenation and the approval outcome check. They are listed below in the order they appear in the flow.

@split(parameters('EnvVar_RSSFeedURLs'),',')

@first(body('Translate_Review'))?['TranslatedText']

@if(greater(length(body('Filter_Negative_Keywords')),0),'Negative','Neutral')

@mul(length(body('Filter_Negative_Keywords')),-1)

@or(equals(outputs('Compose_Sentiment'),'Negative'), greater(length(body('Filter_Notable_Keywords')),0))

Customize & download