Cluster 1,000 keywords, for free

Powered by MeaningCloud, with this script you can input a range of data (1000 cells max) and it will automatically cluster keywords into relevant groups (20k request per month). 🚀

Check out the GIF to see it in action 🎥

---

How to add the Script to Google Sheets

1. Sign up to MeaningCloud

Sign up to MeaningCloud an awesome API for text analysis and natural language processing. You get 20,000 requests per month, for free!

---

2. Get your API Key

Head to the subscriptions page and copy your API key.

---

3. Copy the script below:

/**
 * Automatically assign keywords into clusters. 
 *
 * @param {A2:A1000} range - input the range of your keywords.  
 * @param {"en"} language - [OPTIONAL] input the target language ('en', 'es', 'it', 'fr', 'pt'). Default set to 'en'. 
 * @customfunction
 */

function cluster(range, language) {

    // get the range of keywords
    const keywords = [];
    for (i = 0; i < range.length; i++) {
        keywords.push(range[i][0]);
    }

    // add keywords as line items for request
    const txt = keywords.toString().replace(/,/g, '\n');

    try {
        // MeaningCloud https://api.meaningcloud.com/clustering-1.1
        const apiKey = 'ADD API KEY HERE';
        const lang = language || 'en';

        const requestBody = {
            'key': apiKey,
            'txt': txt,
            'lang': lang
        };

        const options = {
            'method': 'POST',
            'contentType': 'application/x-www-form-urlencoded',
            'payload': requestBody
        };

        const response = UrlFetchApp.fetch('https://api.meaningcloud.com/clustering-1.1', options);
        const result = response.getContentText();
        
        // parse result
        json = JSON.parse(result);

    } catch (e) {
        return 'Request to API failed. Try clustering less keywords';
    }

    const list = json.cluster_list;

    // loop through response and create return array with cluster groups and keywords
    let rows = [],
        data,
        title;
    for (i = 0; i < list.length; i++) {
        data = list[i];
        title = data.title.toLowerCase();
        cluster = Object.values(data.document_list);

        for (j = 0; j < cluster.length; j++) {
            rows.push([title, cluster[j]]);
        }
    }

    // add headers
    rows.unshift(["Cluster Group", "Keywords"]);

    return rows;

}

---

5. Head over to Google Sheets

Or if you’re really smart, create a new sheet by going to: https://sheets.new

Select Apps Script from the Extensions menu.

Paste the script and replace line 22 with your API key:

  const apiKey = 'ADD API KEY HERE';

Save it.

---

6. Add the formula to any cell in your sheet

=cluster(A2:A1000, "en")

You can replace A2:A1000 with any keyword range in a single column. Anything above 1000 cells tends to timeout with this custom function, though I have ran it with 2000 cells successfully. For larger sites, it will be more effective to cluster keywords using this function on a page-by-page basis.

You can also specify a language (the default is set to the ‘en’). The languages supported by MeaningCloud are ‘en’, ‘es’, ‘it’, ‘fr’, and ‘pt’.

*keywords can be part of multiple cluster groups.

---

How does the clustering work?

Here’s the MeaningCloud explanation:

“It groups documents together not by applying a purely textual similitude, but according to their relevance with regard to the subjects present in the collection, and automatically assigns to each cluster a title or name that represents its prevailing subject. Also, it internally employs lemmatization technologies which enable to take into account all the variants of a term, and it can be configured to consider stopwords and other linguistic aspects.”

You can find out more information by visiting their website.

---

Are there better ways to cluster keywords?

In short, yes. This function provides a great, quick (and free) way to automatically group keywords but there are professional clustering tools that cluster keywords based on the similarity of their search results. That means if search results from keyword a match keyword b, they’re grouped together.

With this approach you’re seeing clusters through the lens of Google (sort of) and that makes the data more meaningful. Here’s a list of some fantastic tools on the market if you want to explore this further:

• Keyword Insights
• SE Ranking
• Serpstat
• Cluster AI
• Topvisor

---

More Scripts

• ‘Award-winning’ digital PR headlines with GPT-3
• Append your keywords with all locations, from any country
• Automatically generate title tags & meta descriptions with GPT-3
• Bulk check indexing and coverage reports in Google Sheets