{
  "fetched_at": "2026-10-20T10:03:38Z",
  "source_url": "https://www.kaggle.com/competitions/bmm497-assignment3/data",
  "pages": [
    {
      "name": "rules",
      "content": "This is a page where you can include rules that participants must accept before joining. You may wish to include rules like:\n\n - Don't cheat!\n - Apply yourself!\n - Have fun!",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "data-description",
      "content": "<p>For the document classiffication task, you will classify a given list of movies based on their topic. The movie dataset contains short movie plots. Each movie plot is associated with a label that represents its genre. There are six genres in the dataset:</p>\n<ul>\n<li> Sci-fi</li>\n<li> Action</li>\n<li> Comedy</li>\n<li> Fantasy</li>\n<li> Animation</li>\n<li> Romance</li>\n</ul>\n<h2>Data fields</h2>\n<ul>\n<li><strong>movie_id</strong> - the id of a movie</li>\n<li><strong>movie_genre</strong> - the genre of a movie</li>\n</ul>",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Description",
      "content": "<p>Distributional semantics can represent also a larger chunk of text that consists of words,\nsuch as phrases, sentences and documents. In this task, you will build document representations\nbased on doc2vec [2]. \n\n</p><p>Doc2vec is an unsupervised algorithm to generate vectors for sentence/paragraphs/documents that represent a larger text in a low dimensional space similar to word embeddings. The algorithm is an adaptation of word2vec. Once you learn the document embeddings, you will train a classiffer to group a set of documents based on their topic.\n\n</p><p>You will train doc2vec model using Gensim3 in Python and train Logistic Regression classiffer using a library. You are free to use any library for the classiffer, but we recommend sckitlearn.</p>",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Evaluation",
      "content": "<p>Once you train your classiffier on the training data, and predict the genres of the movies\nin the dataset, you will measure the accuracy of your document classiffier . The accuracy\nis defined as the ratio of the correctly classiffied documents to the total number of\ndocuments:</p>\n<p>\\[ A(W) = \\frac{#_of_correctly_classified_documents}{#_of_documents} \\]</p>\n",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    }
  ]
}