Reviews & AI Insights — Trustpilot, App Store & Google Play

All public reviews for a company or app across Trustpilot, the Apple App Store and Google Play in one schema, with ratings, dates, storefront country and company replies. Optional AI insights: themes, pain points, praise, feature requests and competitor mentions, in English or Arabic. Alerts for new and negative reviews.

جمع تقييمات ومراجعات أي شركة أو تطبيق من ترست بايلوت وآب ستور وجوجل بلاي في مخطط واحد موحّد، مع تحليل ذكي للمواضيع ونقاط الألم وطلبات الميزات — بالعربية الفصحى أو الإنجليزية، وتنبيهات فورية للمراجعات السلبية الجديدة.

Who it's for

• Product teams turning hundreds of reviews into a themed backlog instead of reading them all.
• CX and support leads who need to know within a day when a bad review lands.
• Agencies and competitive-intel analysts tracking several companies and apps at once.
• Investors checking whether a portfolio company's app ratings are trending up or down.
• App publishers watching Gulf storefronts (sa, ae, eg) alongside us and gb.

What makes it different

• Three sources, one schema. A Trustpilot review, an App Store review and a Google Play review come back with the same fields and the same 1–5 rating scale; app reviews are tagged with the storefront country.
• Gulf storefronts. Each country has its own reviews, so adding sa, ae or eg next to us and gb is how you get Arabic and Gulf feedback.
• Company replies from Trustpilot and Google Play, so you can see which complaints were answered.
• Arabic and English insights. Analysis is written in Modern Standard Arabic when you ask for it, while quotes stay in the language they were written in.
• Alerts, not dumps. Change mode returns only new reviews, negative reviews, rating drops and newly added replies.
• Anonymized at the source. No reviewer names, handles, avatars or profile links ever enter the dataset — they are stripped in the source adapters, before a record is built.
• Explicit results. A company or app that cannot be found, a store that returns nothing matching your filters, or AI insights that could not be produced each get a free status row with the reason.

Input

This is the Console prefill: Notion on Trustpilot and both app stores, US and Saudi storefronts, 10 reviews per source, with AI insights. It finishes in about 20 seconds and costs about $0.17:

{
    "targets": [
        {
            "name": "Notion",
            "website": "https://notion.so",
            "appStoreId": "1232780281",
            "googlePlayId": "notion.id"
        }
    ],
    "sources": ["trustpilot", "appstore", "googleplay"],
    "countries": ["us", "sa"],
    "maxReviewsPerSource": 10,
    "aiInsights": true,
    "proxyConfiguration": {
        "useApifyProxy": true
    }
}

website (or trustpilotDomain) is what Trustpilot needs. maxReviewsPerSource caps each app store across all countries, so raise it when you add storefronts. Pass appStoreId and googlePlayId when you know them; otherwise they are looked up from name, and a name that matches no app returns a status row instead of another app's reviews.

Output

Four item types, told apart by itemType, all documented in .actor/dataset_schema.json: review, summary (per target × source), insights (per target) and alert (change mode). The Console shows Reviews, Insights and Alerts views.

A review, from the example input above:

{
    "itemType": "review",
    "source": "googleplay",
    "target": "Notion",
    "productName": "Notion: Notes, Tasks, AI",
    "reviewId": "3dcccbe4-2252-4b02-a16a-4664c3d5bc8c",
    "url": "https://play.google.com/store/apps/details?id=notion.id&reviewId=3dcccbe4-2252-4b02-a16a-4664c3d5bc8c",
    "rating": 5,
    "title": null,
    "text": "great",
    "language": "en",
    "publishedAt": "2026-09-12T00:44:16.995Z",
    "country": "us",
    "appVersion": "0.6.3943",
    "verified": null,
    "helpfulCount": 0,
    "companyReply": null,
    "scrapedAt": "2026-09-13T01:55:37.531Z"
}

The insights item from the same run (lists shortened):

{
    "itemType": "insights",
    "target": "Notion",
    "overallSentiment": 0.06,
    "themes": [
        {
            "theme": "Mobile app usability",
            "sentiment": -0.85,
            "count": 6,
            "shortQuotes": [
                "It is really confusing to work with",
                "mobile app feels so clunky",
                "iPad app is genuinely unusable due to bugs"
            ]
        },
        {
            "theme": "Performance and stability",
            "sentiment": -0.9,
            "count": 4,
            "shortQuotes": ["insanely slow loading", "constant crashes", "cursor teleports somewhere else"]
        }
    ],
    "painPoints": ["PDF files cannot be opened directly", "Toggle feature missing", "App can feel slow"],
    "praise": [
        "Great, amazing, wonderful experience",
        "Love the AI not being forced",
        "Preferred for note taking and templates"
    ],
    "featureRequests": [
        "Add direct PDF import capability",
        "Implement toggle feature for typing",
        "Improve overall performance speed"
    ],
    "competitorMentions": [
        {
            "competitor": "Google Docs",
            "count": 1,
            "context": "consider migrating to Google Docs"
        }
    ],
    "suggestedActions": [
        "Fix PDF import functionality",
        "Add the missing toggle feature",
        "Optimize app performance to reduce slowness"
    ],
    "sourceBreakdown": {
        "googleplay": 10,
        "appstore": 10
    },
    "reviewsAnalyzed": 20,
    "language": "en",
    "scrapedAt": "2026-09-13T01:55:41.243Z"
}

Status rows use itemType: "alert" with type: "source_error" (or no_changes in alert mode) and the reason in error, for example No App Store app found for this name; add appStoreId or appStoreUrl to the target. They are never charged.

Sample output

Real items from the example input above (a Trustpilot review, an App Store review and the AI insights record), verified on the Apify platform in September 2026. Reviewer identities are never collected. Long text and lists are shortened for this page; field names and values are otherwise exactly as the Actor returns them.

[
    {
        "itemType": "review",
        "source": "trustpilot",
        "target": "Notion",
        "productName": "Notion",
        "reviewId": "6aa306ce3b8a636e2d1861f5",
        "url": "https://www.trustpilot.com/reviews/6aa306ce3b8a636e2d1861f5",
        "rating": 1,
        "title": "Notion Sends Your Proprietary Business Data to OpenAI",
        "text": "Turns out notion was sending all of our proprietary business data to OpenAI. If you read the small print you can find this, but it should BE FRONT AND CENTER. As a business it is extremely alarming that this would be in a hard to find place especially given the fact that OpenA…",
        "language": "en",
        "publishedAt": "2026-09-10T21:36:46.000Z",
        "country": null,
        "appVersion": null,
        "verified": false,
        "helpfulCount": 0,
        "companyReply": null,
        "scrapedAt": "2026-09-13T20:59:56.980Z"
    },
    {
        "itemType": "review",
        "source": "appstore",
        "target": "Notion",
        "productName": null,
        "reviewId": "14538800387",
        "url": "https://itunes.apple.com/us/review?id=1232780281&type=Purple%20Software",
        "rating": 1,
        "title": "no more ai",
        "text": "so sick of corporations forcing ai in my face and down my throat you can just be a regular productivity app like you used to be",
        "language": "en",
        "publishedAt": "2026-09-11T23:19:27.000Z",
        "country": "us",
        "appVersion": "1.7.334",
        "verified": null,
        "helpfulCount": 0,
        "companyReply": null,
        "scrapedAt": "2026-09-13T20:59:56.982Z"
    },
    {
        "itemType": "insights",
        "target": "Notion",
        "overallSentiment": -0.05,
        "themes": [
            {
                "theme": "Organization/Structure",
                "sentiment": 1,
                "count": 4,
                "shortQuotes": ["well organised app", "melhor app da vida!", "facilitado... organizar"]
            },
            {
                "theme": "Performance and stability",
                "sentiment": -0.78,
                "count": 4,
                "shortQuotes": ["extremely laggy for me", "super slow response", "insanely slow loading"]
            },
            {
                "theme": "Mobile app usability",
                "sentiment": -0.71,
                "count": 3,
                "shortQuotes": [
                    "clunky and misses important features",
                    "iPad app is genuinely unusable due to bugs",
                    "viewport moves to somewhere else on the document"
                ]
            }
        ],
        "painPoints": ["Too tough to use", "High price ($200+)", "AI activation limited to after five hours"],
        "praise": [
            "Well‑organized and flexible for planning",
            "Never crashes, stable performance",
            "AI not forced on users"
        ],
        "featureRequests": [
            "Allow AI activation sooner or on demand",
            "Introduce lower‑cost pricing tiers",
            "Add a simple “my tasks” view on mobile"
        ],
        "competitorMentions": [
            {
                "competitor": "Google Docs",
                "count": 1,
                "context": "consider migrating to Google Docs due to mobile issues"
            }
        ],
        "suggestedActions": [
            "Simplify onboarding and UI to reduce usability friction",
            "Review pricing strategy or add affordable plans",
            "Clarify AI activation policy and provide user‑controlled options"
        ],
        "sourceBreakdown": {
            "googleplay": 10,
            "appstore": 10,
            "trustpilot": 10
        },
        "reviewsAnalyzed": 30,
        "language": "en",
        "scrapedAt": "2026-09-13T21:00:10.995Z"
    }
]

Alerts and scheduling

1. Set emitChangesOnly and a trackingId, then Save as task.
2. Add a Schedule — daily is typical, hourly if you are in a launch week.
3. Under Integrations, send results to Slack, Email, a Webhook, Make or Zapier on Run succeeded. In change mode a quiet run contains a single free no_changes row, so filter on type to hear only about real alerts.
4. Route by type: send negative_review and rating_drop to a human, log new_review.

The first run for a tracking ID records a baseline and returns one no_changes row saying so, so your first alert is a real one.

n8n and Make

Use the Apify node with Run Actor and get dataset, then filter on type == "negative_review" to open a ticket, or on rating_drop to notify a lead.

Use as an API (Standby)

The Actor runs in Standby mode, so a workflow or an AI agent can ask for reviews per HTTP request:

GET https://almoutasem-nabil--review-intelligence.apify.actor/?target=Notion&sources=appstore,googleplay&maxReviewsPerSource=10&aiInsights=1
Authorization: Bearer <your Apify token>

Parameters mirror the input (target, sources, countries, lastNDays, maxReviewsPerSource, aiInsights, insightsLanguage, trackingId), charged with the same events as a normal run. GET /health returns {"ok":true}.

Pricing

Pay-per-event. You pay for sources read, reviews returned and analysis produced.

Event	Price	When
Source checked	$0.005	Per target × source fetched successfully. A failed source is free.
Review	$0.002	Per normalized review stored.
AI insight batch	$0.03	Per batch of 10 reviews analyzed; the rollup is included.
Alert	$0.01	Change mode, per alert. Source errors are free.

• The example input above: 3 × $0.005 + 30 × $0.002 + 3 × $0.03 = $0.165.
• 500 reviews across the three sources for one company: 3 × $0.005 + 500 × $0.002 = $1.015.
• AI insights over those 500 reviews (50 batches): $1.50.
• Daily alerts for 10 competitors on the three sources: about $0.15 a day, plus $0.01 per alert.

Default memory is 1024 MB, which covers the headless browser Trustpilot needs. App-store-only runs never start the browser. No residential proxies are used: all three sources work with the default datacenter proxy.

Per-source notes and limitations

• Trustpilot — Trustpilot refuses plain HTTP clients, so its review pages are loaded in a headless browser (through the default datacenter proxy), paced to one page per second, and read from the page's embedded data (20 reviews per page, with company replies and verification labels). A company Trustpilot does not list returns a status row; set trustpilotDomain when Trustpilot uses a different domain than website.
• Apple App Store — Apple's public customer-reviews feed, per storefront. Reliable and fast. The feed carries no developer replies, so companyReply is null for App Store reviews.
• Google Play — through the maintained google-play-scraper package, including developer replies.
• Reviews with no date are kept rather than dropped, so a source that omits dates is not silently filtered away by lastNDays.
• AI insights analyze reviews in batches of 10; each batch is billed once it is analyzed.

Related actors

• ../hiring-signals-monitor — track companies' career pages.
• ../ad-library-intelligence — track competitors' live ads.
• ../page-change-monitor — track any page for changes.

Legal note

The Actor reads publicly published reviews — the same content any visitor sees — and never logs in or sends cookies. It collects no reviewer identity: names, handles, avatars and profile links are stripped in the source adapters before a record is built, and contact details pasted into review text are redacted. Quotes inside AI insights are short excerpts of at most 15 words, never whole reviews. Review text remains the work of its authors and the property of the platform that hosts it; use the output for analysis in line with each source's terms and the laws that apply to you. Trustpilot, Apple and Google are trademarks of their owners; this Actor is not affiliated with them.

Roadmap

Not available yet:

• G2 and Capterra. Both block automated traffic and publish no feed; their parsers will be built once their pages can be fetched reliably.