{
  "fetched_at": "2026-10-19T20:39:40Z",
  "source_url": "https://www.kaggle.com/competitions/education-level-prediction-trough-comments/data",
  "pages": [
    {
      "name": "data-description",
      "content": "This dataset contains a list of comments delivered to content creators, it contains a list of feature extractions trough NLU that provide context to the particular text string, weather it is referencing particular individuals, countries, or organizations. \nFinally it gives a sentiment score of the particular string giving the context. Your goal is to as accurately as possible determine whether the comment was positive 1,  neutral 0 or negative -1. \n\n\n\nWhat files do I need? \nthe training dataset will provide you with a base features and target of the sentiment evaluated by our algorithm,\nthe comment that was analyzed and some features of the context in the text, your goal is to tokenize, classify  and vectorize the words in the comments so they can be matched with positive neutral or negative emotions.\n \nWhat should I expect the data format to be?  \nstraight foreword csv file. \n\n\nWhat am I predicting?  \nthe overall sentiment of comments summited to content creators, you must determine in a spectrum whether the sentiment behind the text is positive, negative or neutral.\n\n\nWhat acronyms will I encounter?\nvideo_id: YT video from witch the comment was extracted\ncomments: the comment you need to work with to determine the final sentiment analysis.\nFACILITY,  entity recognition of a facility.\nLOCATION, entity recognition of a person.\n GPE, entity recognition of a geopolitical event.\nORGANIZATION, entity recognition of a organization.\nPERSON, entity recognition of a person or individual.\nsentiment, determines the score of the analysis of the text.\n",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Description",
      "content": "**Goal of the competition**\nThe main target of this competition is to be able to classify emotion and context of written Spanish based on up to date idiom and focused specifically on input given to content creators. Our goal was to create an accurate NLU that gives hindsight to content creators about their audience, and help them decide the topics and intellectual property for further content.\n\nViewers feedback , whether positive or negative,  will encourage the content creator to make improvements.\n\nIn this competition you will work with a challenging dataset consisting in a variety of attributes describing the context and sentiment viewers described. and you have to predict the overall sentiment of the comment, whether is positive or negative in the context, or if it is not relevant  for the creator.\n\nWe hope you have fun and we are eager to see what creative solutions you come up with to generate a comprehensive understanding of the Spanish language\n\n## Acknowledgements\n\nWe thank Metacube entertainment for providing the dataset",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Evaluation",
      "content": "Submissions are evaluated using ussing a weighted multi level logarithmic loss, \n---\n\nThe evaluation metric for this competition is [Mean F1-Score](https://en.wikipedia.org/wiki/F-score). The F1 score, commonly used in information retrieval, measures accuracy using the statistics precision \\( \\text{p} \\) and recall \\( \\text{r} \\).\n\nPrecision is the ratio of true positives \\(\\text{tp}\\) to all predicted positives \\(\\text{tp} + \\text{fp}\\). Recall is the ratio of true positives \\(\\text{tp}\\) to all actual positives \\(\\text{tp} + \\text{fn}\\). The F1 score is given by:\n\n\\[ \\text{F1} = 2\\frac{\\text{p} \\cdot \\text{r}}{\\text{p}+\\text{r}}\\ \\ \\mathrm{where}\\ \\ \\text{p} = \\frac{\\text{tp}}{\\text{tp}+\\text{fp}},\\ \\ \\text{r} = \\frac{\\text{tp}}{\\text{tp}+\\text{fn}} \\]\n\nThe F1 metric weights recall and precision equally, and a good retrieval algorithm will maximize both precision and recall simultaneously. Thus, moderately good performance on both will be favored over extremely good performance on one and poor performance on the other.\n",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "rules",
      "content": " - Don't cheat!\n - Apply yourself!\n - Have fun!\n\n Easter egg: we would love to see also how you assigned labels to individual tokens to better manage the entity recognition patterns, please contact us if you have a creative solution to this particular problem.",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    }
  ]
}