[Cotlet](https://cotlet.dev/index.md) · [Integrations](https://cotlet.dev/integrations.md) · [How it works](https://cotlet.dev/how-it-works.md) · [Use cases](https://cotlet.dev/use-cases.md) · [Security](https://cotlet.dev/security.md) · [For developers](https://cotlet.dev/for-developers.md) · [For automation agencies](https://cotlet.dev/for-agencies.md) · [Blog](https://cotlet.dev/blog.md) · [API docs](https://cotlet.dev/docs.md) · [Help center](https://cotlet.dev/help.md) · [Changelog](https://cotlet.dev/changelog.md) · [Contact](https://cotlet.dev/contact.md) · [Pricing](https://cotlet.dev/pricing.md) · [Sign up](https://cotlet.dev/signup)

# Correct wrong sentiment on Brand24 mentions

> Fix Brand24 sentiment by your own rules, such as sarcasm or product names, so the charts and PDF reports show the real mood. Runs weekly.

Source: https://cotlet.dev/integrations/brand24-api-mcp-server/correct-mention-sentiment

Brand24 scores every mention as positive, neutral or negative on its own, and a sarcastic review or a product name with a gloomy word skews the Sentiment chart you send to a client.

Cotlet does it in your own Brand24 account with get\_project\_stats, list\_mentions and set\_mention\_sentiment, called by your AI agent, an n8n workflow or a script.

[Sign up free](https://cotlet.dev/app/signup?app=brand24) [All Brand24 tools](https://cotlet.dev/integrations/brand24-api-mcp-server.md)

Hosted · nothing to install or maintain

## Can Brand24 do this on its own?

Brand24 changes sentiment only by hand (checked 23 Oct 2026). Its API reference has an endpoint for sentiment counts and none that changes a mention's sentiment, and its MCP server documents no write.

## How you do it in Brand24 today

1. Open the Mentions tab of the project and filter the list to the sentiment you want to review.
2. Click the sentiment shown on a mention and choose positive, neutral or negative.
3. For several mentions, tick their boxes or click Select all, and choose Change sentiment in the bulk actions bar.
4. Look at the Sentiment chart on the Mentions tab, which plots positive and negative mentions over time.
5. Before sending a PDF report, open the PDF Creator and check the Sentiment and Sentiment by Categories slides.

## How to correct wrong sentiment on Brand24 mentions

Prompt

```
In the Northwind Coffee project, look at this week's negative mentions. Set the ones that are sarcastic praise or about "dark roast" to positive, and tell me how the sentiment counts changed.
```

1. 01  
### Take the counts before  
get\_project\_stats gives positive, neutral and negative counts for the week. The agent keeps them to report the change at the end.
2. 02  
### Pull the mentions to review  
list\_mentions runs with sentiment set to negative and a query for the misleading words you named, such as the product name "dark roast". The agent follows next\_cursor, so a long week is judged as one batch.
3. 03  
### Judge with your rule  
The agent reads each title against your rule and quotes the words it relied on. Sarcasm that praises and a product name are moved. A real complaint stays as it is.
4. 04  
### Set the new sentiment  
set\_mention\_sentiment runs once per target sentiment with all matching IDs. It reaches no one and a second call reverses it, so it does not wait for your OK.
5. 05  
### Report the shift  
get\_project\_stats runs again over the same week and the agent shows both sets of counts side by side.

### What you get back

Example data

```
Northwind Coffee, 12 to 18 Oct: 315 mentions
Checked 45 negative mentions
Changed 6 to positive (4 sarcastic praise, 2 about "dark roast")
Negative 45 to 39, positive 120 to 126, neutral 150
Kept 39 as negative, e.g. "Grinder arrived with a cracked hopper"
```

### Other ways to ask

- Check neutral mentions from news sites and set the ones that praise the product to positive.
- Set every mention that mentions a competitor's name in the title to neutral.
- List the mentions you would change, with your reason, and change nothing until I say so.
- Before I export the monthly PDF report, fix the sentiment of the 20 most popular mentions.

## What Brand24 allows, and what to know first

- Brand24 lets you change the sentiment of a mention manually to positive, neutral or negative in the Mentions tab.
- Change sentiment is one of four bulk actions in the Mentions tab, so a whole batch can be changed in one step.
- The Sentiment chart on the Mentions tab plots positive and negative mentions over time.
- The PDF report builder has Sentiment and Sentiment by Categories slides under Analysis, and PDF reports are in the Pro, Business and Enterprise plans.
- Brand24's API returns sentiment counts for a project and has no endpoint that changes the sentiment of a mention.

set\_mention\_sentiment changes only your own Brand24 data and reach no one else, so it runs without asking first.

Sources: [Brand24 Help: Mentions tab overview](https://help.brand24.com/en/articles/9772539-mentions-tab-overview) · [Brand24 Help: Bulk actions](https://help.brand24.com/en/articles/9686105-bulk-actions) · [Brand24 Help: PDF Report](https://help.brand24.com/en/articles/5336578-pdf-report) · [Brand24 API Data Documentation](https://api-data.brand24.com/api-data-docs/documentation)

## Call set\_mention\_sentiment from a script

curl

```
curl -X PUT https://cotlet.dev/api/v1/brand24/projects/123456789/mention-sentiment \
  -H "Authorization: Bearer $COTLET_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"mention_ids":["7001234530","7001234531"],"sentiment":"positive"}'
```

Example response

```
{
"updated": 2,
"sentiment": "positive"
}
```

MCP: add https://cotlet.dev/mcp/v1 with the same key; the call is brand24\_write → set\_mention\_sentiment. Example data.

[Schedule it in n8n, Make, Zapier or cron](https://cotlet.dev/integrations/brand24-api-mcp-server.md#automations)

## Brand24 tools this automation uses

__Cotlet Brand24 tools used to correct wrong sentiment on Brand24 mentions__
| Tool | Parameters |
| ----------------------- | ---------------------------------------------------------------------- |
| get\_project\_stats | project\_id, date\_from, date\_to |
| list\_mentions | project\_id, date\_from, date\_to, query, sentiment, tag, sort, cursor |
| set\_mention\_sentiment | project\_id, mention\_ids, sentiment |

[All 10 Brand24 tools with descriptions](https://cotlet.dev/integrations/brand24-api-mcp-server.md#tools)

## Frequently asked questions

### Is it safe to connect Brand24 to Cotlet?

Yes. You sign in to Brand24 yourself, in your own Cloud Browser in the EU, and we never save your password. Your agents only get Brand24 once you enable it, every background request is listed, and the browser profile is stored encrypted with AES-256-GCM, the cipher 1Password uses for its vaults. The AI model never sees a login, posts and messages wait for your OK, and Disable for agents cuts access in one click. Independent scanners grade cotlet.dev A+ on Qualys SSL Labs, securityheaders.com and Mozilla Observatory; live results are on https://cotlet.dev/security.

## More Brand24 automations

- [Delete irrelevant Brand24 mentions and block junk sources](https://cotlet.dev/integrations/brand24-api-mcp-server/clean-up-irrelevant-mentions.md)
- [Tag Brand24 mentions as complaints, leads and questions](https://cotlet.dev/integrations/brand24-api-mcp-server/tag-mentions-automatically.md)
- [Brand24 API and MCP server: every tool](https://cotlet.dev/integrations/brand24-api-mcp-server.md)
- [All use cases](https://cotlet.dev/use-cases.md)

## Give your agent access to Brand24.

Free 7-day trial with 2,000 credits, no card needed. Cotlet is independent and not affiliated with Brand24.

[Sign up free](https://cotlet.dev/app/signup?app=brand24)

---

Give your AI agents your signed-in browser.

**Product:** [Integrations](https://cotlet.dev/integrations.md) · [Use cases](https://cotlet.dev/use-cases.md) · [How it works](https://cotlet.dev/how-it-works.md) · [Pricing](https://cotlet.dev/pricing.md) · [Security](https://cotlet.dev/security.md)

**Resources:** [Blog](https://cotlet.dev/blog.md) · [API docs](https://cotlet.dev/docs.md) · [Help center](https://cotlet.dev/help.md) · [Changelog](https://cotlet.dev/changelog.md) · [GitHub](https://github.com/cotletdev/cotlet)

**Solutions:** [For developers](https://cotlet.dev/for-developers.md) · [For automation agencies](https://cotlet.dev/for-agencies.md)

**Company:** [About](https://cotlet.dev/about.md) · [AI info: company facts](https://cotlet.dev/ai-info.md) · [Contact](https://cotlet.dev/contact.md)

**Legal:** [Terms of service](https://cotlet.dev/terms) · [Privacy policy](https://cotlet.dev/privacy) · [Refund policy](https://cotlet.dev/refunds) · [Acceptable use](https://cotlet.dev/acceptable-use) · [Cookie policy](https://cotlet.dev/cookies) · [DPA](https://cotlet.dev/dpa) · [Subprocessors](https://cotlet.dev/subprocessors)

**Elsewhere:** [Status page](https://status.cotlet.dev) · [Cotlet on GitHub](https://github.com/cotletdev) · [Cotlet on X](https://x.com/cotletdev) · [Cotlet on LinkedIn](https://www.linkedin.com/company/cotletdev) · [Cotlet on Product Hunt](https://www.producthunt.com/products/cotlet) · [Cotlet on Crunchbase](https://www.crunchbase.com/organization/cotlet) · [Cotlet on SaaSHub](https://www.saashub.com/cotlet)

Cotlet.dev is built by Bart Krawczyk and Jake Slugocki, the founders of Take Group sp. z o.o., ul. Wincentego Janasa 4, 40-855 Katowice, Poland. KRS 0000871398, NIP 6342984273, VAT EU: PL6342984273. [About us](https://cotlet.dev/about.md)

Cotlet is an independent service. It is not affiliated with, endorsed by or sponsored by any of the products listed on this site. Product names are trademarks of their respective owners.