{
  "fetched_at": "2026-10-19T23:24:18Z",
  "source_url": "https://www.kaggle.com/competitions/bda-2018-19-sem2-test-competition/data",
  "pages": [
    {
      "name": "rules",
      "content": "<h3>Data</h3>\n<p>The data were kindly provided. Please help protect the privacy of individuals who contributed to the data set by not downloading or sharing the data.</p>\n<h3>Leveling the playing field</h3>\n<p>Because of the wide range of backgrounds of your peers, you can only use the methods discussed in the book in Chapter 3 of the ISLR book. Any use of any other methods will automatically disqualify your submission.<p>\n<h3>Team effort</h3>\n<p>You work in teams of 2 members (3 only if absolutely necessary). Each team submits their work as a team. For this competition each team can enter 2 submissions. The second submission should be made right before the closing deadline; that is, only <b>after</b> your presentations about your first submission. Take advantage of your second submission to improve your team's position on the leaderboard. That is, learn from the other teams presentations and 'steal' their good ideas!</p>\n\n<!-- Begin Base Rules -->\n<h3>One account per participant</h3>\n<p>You cannot sign up to Kaggle from multiple accounts and therefore you cannot submit from multiple accounts.</p>\n<h3>No private sharing outside teams</h3>\n<p>\n    Privately sharing code or data outside of teams is not permitted.\n    It's okay to share code if made available to all participants on the forums.\n</p>\n<h3>Team Mergers</h3>\n<p>Team mergers are not allowed in this competition.</p>\n\n<h3>Team Limits</h3>\n<p>The maximum team size is 2 members.</p>\n<h3>Submission Limits</h3>\n<p>You may submit a maximum of 2 entries per day.</p>\n<p>You may select up to 2 final submissions for judging.</p>\n<h3>Competition Timeline</h3>\n<p>Start Date: <strong>TBA</strong></p>\n<p>Merger Deadline: <strong>None</strong></p>\n<p>Entry Deadline: <strong>None</strong></p>\n<p>End Date: <strong>2/1/2014 12:00 AM UTC</strong></p>\n<!-- End Base Rules -->",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "data-description",
      "content": "<h2>File descriptions</h2>\n<ul>\n<li><strong>essaytrain.csv</strong> - the training set</li>\n<li><strong>essaytest.csv</strong> - the test set</li>\n<li><strong>sample_submission.csv</strong> - a sample submission file in the correct format</li>\n</ul>\n<h2>Data fields</h2>\n<ul>\n<li><strong>#AUTHID</strong> - an anonymous id unique to a given essay author</li>\n<li><strong>TEXT</strong> - the full essay text as a string</li>\n<li><strong>cEXT</strong> - the profile label (y or n) on the Extraversion scale</li>\n<li><strong>cNEU</strong> - the profile label (y or n) on the Neuroticism scale</li>\n<li><strong>cAGR</strong> - the profile label (y or n) on the Agreeableness scale</li>\n<li><strong>cCON</strong> - the profile label (y or n) on the Conscientiousness scale</li>\n<li><strong>cCON</strong> - the profile label (y or n) on the Openness scale</li>\n</ul>\nThe last 5 columns form the personality profile, each labelled with 'y' or 'n'. These are the target variables for which a prediction is needed in the test set.",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Description",
      "content": "<p>In this competition the challenge for your team is to predict personality profiles from essay texts. The data set consists of essay texts , combined with Big 5 personality profiles of their authors. The personality profiles were derived from median split binary categorization of the IPIP personality questionnaire scores. The personality profile axes can be interpreted as follows:\n</p>\n<ul>\n<li><b>cEXT</b> Extraversion: sociable ('y') vs shy ('n')\n</li><li><b>cNEU</b> Neuroticism: neurotic ('y') vs calm ('n')\n</li><li><b>cAGR</b> Agreeableness: friendly ('y') vs uncooperative ('n')\n</li><li><b>cCON</b> Conscientiousness: organized ('y') vs careless ('n')\n</li><li><b>cOPN</b> Openness: insightful ('y') vs unimaginative ('n')\n</li>\n<p>Your team should employ any of the methods discussed in chapters 1 through 3 of ISLR, in combination with creative feature engineering and feature selection, to obtain the best binary predictions for all the personality axes. </p>\n<p><b>No other methods than the ones mentioned in ISLR chapters 1 through 3 may be used. Doing so disqualifies your team.</b></p>\n<p>Please note that the file format in which you need to upload your team's predictions is different from the file format of the data set.</p></ul>",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Evaluation",
      "content": "<p>The evaluation of your team's predictions accuracy is measured the percentage of correct predictions as aggregated across all test set authors across all personality axis. That is, the performance is computed as\n\\[\n\\sum_{a \\in \\{cEXT, cNEU, cAGR, cCON, cOPN\\}} \\sum_{i\\in\\text{Test set authors}} I(y_{ia} = \\hat y_{ia})/N.\n\\]\nHere\n\\[\n\\begin{align}\ny_{ia} &amp;\\qquad \\text{is the observed label for personality axis $a$ for the $i$-th author in the test set, and} \\\\\n\\hat y_{ia} &amp;\\qquad \\text{is the corresponding predicted label.}\n\\end{align}\n\\]\nFurthermore N is the size of the test set, and\n\\[ I(x) = \\begin{cases} 1 &amp; \\text{if $x = TRUE$} \\\\ 0 &amp; \\text{if $x=FALSE$}\\end{cases} \\]\n</p><hr>\n\n\n<h2>Submission Format</h2>\n\n<p><strong>For every author in the dataset</strong>, submission files should contain two columns: Id and value. The Id column identifies the test set author and personality axis, by means of concatenating the <code>#AUTHID</code> string and the axis label (<code>EXT, NEU, CON, AGR</code> or <code>OPN</code>) together with an underscore (<code>_</code>) in between. The value column should contain the predicted label ('y' or 'n'). For example, if for #AUTHID <code>1997_504851.txt</code> your team's prediction is that this person is shy (EXT = 'y'), neurotic (NEU = 'y'), uncooperative (AGR = 'n'), organized (CON = 'y') and unimaginative (OPN = 'n'), then the submission file should contain the rows </p>\n<pre>⋮\n1997_504851.txt_EXT,y\n1997_504851.txt_NEU,y\n1997_504851.txt_AGR,n\n1997_504851.txt_CON,y\n1997_504851.txt_OPN,n\n⋮\n</pre>\n<p>The file should contain a header and have the following format:</p>\n<pre>Id,value\n1997_504851.txt_EXT,y\n1997_504851.txt_NEU,y\n1997_504851.txt_AGR,n\n1997_504851.txt_CON,y\n1997_504851.txt_OPN,n\n⋮\n</pre>",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    }
  ]
}