{
  "$type": "site.standard.document",
  "contributors": [
    {
      "did": "did:plc:igunvse2uemkwmci3igoxhu5",
      "displayName": "Oz Akan",
      "role": "author"
    }
  ],
  "coverImage": {
    "$type": "blob",
    "ref": {
      "$link": "bafkreialgcev5jubyor4avti432zgpx66bzhvrkzjalqcuu2dvhfq3gyva"
    },
    "mimeType": "image/png",
    "size": 312465
  },
  "description": "The goal of TF-IDF is to emphasize words that are important in a particular document while filtering out common words that appear frequently across many documents but offer little unique information.",
  "path": "/techs/tf-idf-simplified",
  "publishedAt": "2025-02-23T21:00:00.000Z",
  "site": "at://did:plc:igunvse2uemkwmci3igoxhu5/site.standard.publication/luminary-blog",
  "tags": [
    "aiml"
  ],
  "textContent": "Term Frequency-Inverse Document Frequency (TF-IDF) is a statistical measure used in Natural Language Processing (NLP) and machine learning to assess the importance of a word within a document relative to a larger collection of documents (corpus). It helps convert text data into numerical representations, making it useful for applications like text classification, document clustering, and information retrieval.",
  "title": "TF-IDF Simplified"
}