Corpus.tools

corpus.tools

Corpus.tools is a joint portal developed by Masaryk University’s NLP Centre and Lexical Computing, providing a suite of open-source software for text corpus processing and natural language processing. The platform offers specialized tools for cleaning, deduplicating, tokenizing, and analyzing large-scale multilingual text datasets to support linguistic research and NLP engineering. Key offerings include NoSketch Engine, JusText, and Spiderling, which streamline the creation and maintenance of high-quality linguistic corpora.

LLM mention score The LLM mention score is the total number of mentions of this brand in different LLM chatbots, normalized to the scale from 0 to 100. You can get actual, non-normalized numbers via the LLM Mention API from DataForSEO.

Normalized 0–100 · last 8 weeks

DataForSEO API

Get LLM mention data of any company via DataForSEO API

Get access to the structured data on keyword, brand, and website mentions in LLMs, including metrics like AI search volume, impressions, and mentions count. 

How to get LLM mention data →
// Fetch Corpus.tools mentions
POST v3/ai_optimization/llm_mentions/search/live
[
    {
        "target": [
            {
                "keyword": "Corpus.tools",
                "search_scope": ["any"]
            }
        ],
        "platform": "chat_gpt",
        "order_by" : ["ai_search_volume,desc"]
    }
]