{
  "id": 248474,
  "title": "Just a coincidence?",
  "url": "/competitions/mlb-player-digital-engagement-forecasting/discussion/248474",
  "author_name": "",
  "post_date": "2021-06-23T17:01:08.627704900Z",
  "votes": 10,
  "comment_count": 6,
  "views": 0,
  "content": "<p>I am trying to figure out what target 1-4 is in the <a href=\"https://www.kaggle.com/c/mlb-player-digital-engagement-forecasting/discussion/247111\" target=\"_blank\">previous</a> topic a few suggested that it might be twitter impression data.</p>\n<p>Looks like it could be predictions of following features of impression on a tweet.</p>\n<ol>\n<li>Number of comment</li>\n<li>Number of retweet</li>\n<li>Number of likes</li>\n<li>Number of shares</li>\n</ol>\n<p>Or is it a coincidence that we are predicting 4 targets and a tweet has exactly 4 measures of impressions on a tweet?</p>",
  "messages": [
    {
      "id": "1362817",
      "postDate": "06/23/2021 17:01:08",
      "content": "<p>I am trying to figure out what target 1-4 is in the <a href=\"https://www.kaggle.com/c/mlb-player-digital-engagement-forecasting/discussion/247111\" target=\"_blank\">previous</a> topic a few suggested that it might be twitter impression data.</p>\n<p>Looks like it could be predictions of following features of impression on a tweet.</p>\n<ol>\n<li>Number of comment</li>\n<li>Number of retweet</li>\n<li>Number of likes</li>\n<li>Number of shares</li>\n</ol>\n<p>Or is it a coincidence that we are predicting 4 targets and a tweet has exactly 4 measures of impressions on a tweet?</p>",
      "rawMarkdown": "I am trying to figure out what target 1-4 is in the [previous](https://www.kaggle.com/c/mlb-player-digital-engagement-forecasting/discussion/247111) topic a few suggested that it might be twitter impression data.\n\nLooks like it could be predictions of following features of impression on a tweet.\n\n1. Number of comment\n2. Number of retweet\n3. Number of likes\n4. Number of shares\n\nOr is it a coincidence that we are predicting 4 targets and a tweet has exactly 4 measures of impressions on a tweet?",
      "votes": null
    },
    {
      "id": "1362860",
      "postDate": "06/23/2021 17:37:43",
      "content": "<p>Hi, <br>\nI think 4 target columns are not directly obtained from twitter's impression data because there are 2061 players but only 1447 twitter accounts in competition dataset. However, players who have twitter account tends to have higher <code>target*</code> value, therefore twitter activity probably have deep relation with <code>target*</code> values. See following short notebook if you are intereseted in!<br>\n<a href=\"https://www.kaggle.com/tomokikmogura/do-all-players-have-twitter-account?scriptVersionId=66455508\" target=\"_blank\">https://www.kaggle.com/tomokikmogura/do-all-players-have-twitter-account?scriptVersionId=66455508</a></p>",
      "rawMarkdown": "Hi, \nI think 4 target columns are not directly obtained from twitter's impression data because there are 2061 players but only 1447 twitter accounts in competition dataset. However, players who have twitter account tends to have higher `target*` value, therefore twitter activity probably have deep relation with `target*` values. See following short notebook if you are intereseted in!\nhttps://www.kaggle.com/tomokikmogura/do-all-players-have-twitter-account?scriptVersionId=66455508",
      "votes": null
    },
    {
      "id": "1362881",
      "postDate": "06/23/2021 17:58:56",
      "content": "<p>That is my thought as well… see this discussion</p>\n<p><a href=\"https://www.kaggle.com/c/mlb-player-digital-engagement-forecasting/discussion/246499\" target=\"_blank\">https://www.kaggle.com/c/mlb-player-digital-engagement-forecasting/discussion/246499</a></p>",
      "rawMarkdown": "That is my thought as well... see this discussion\n\nhttps://www.kaggle.com/c/mlb-player-digital-engagement-forecasting/discussion/246499",
      "votes": null
    },
    {
      "id": "1363135",
      "postDate": "06/24/2021 00:17:34",
      "content": "<p>I was thinking the same. Seems like it does tie nicely to Twitter data. </p>",
      "rawMarkdown": "I was thinking the same. Seems like it does tie nicely to Twitter data.",
      "votes": null
    },
    {
      "id": "1363173",
      "postDate": "06/24/2021 01:54:49",
      "content": "<p>seems like that. after some analysis, I  found out targets are also somewhat correlated to each other looks like twitter gonna be an important feature</p>",
      "rawMarkdown": "seems like that. after some analysis, I  found out targets are also somewhat correlated to each other looks like twitter gonna be an important feature",
      "votes": null
    },
    {
      "id": "1363238",
      "postDate": "06/24/2021 03:53:28",
      "content": "<p>The notebook below takes Mike Trouts tweets from February 2021 to the beginning of May and scales the 4 twitter metrics (retweets, likes, quotes and replies) between 0 and 100 just like the targets - it then plots the different metrics and Mike Trouts targets, from the MLB data, for the same period - after this I  do not think that the targets are the twitter metrics based on this analysis.</p>\n<p><a href=\"https://www.kaggle.com/mlconsult/twitter-data-compare\" target=\"_blank\">https://www.kaggle.com/mlconsult/twitter-data-compare</a></p>",
      "rawMarkdown": "The notebook below takes Mike Trouts tweets from February 2021 to the beginning of May and scales the 4 twitter metrics (retweets, likes, quotes and replies) between 0 and 100 just like the targets - it then plots the different metrics and Mike Trouts targets, from the MLB data, for the same period - after this I  do not think that the targets are the twitter metrics based on this analysis.\n\nhttps://www.kaggle.com/mlconsult/twitter-data-compare",
      "votes": null
    },
    {
      "id": "1364211",
      "postDate": "06/24/2021 17:54:44",
      "content": "<p>thanks for sharing !</p>",
      "rawMarkdown": "thanks for sharing !",
      "votes": null
    }
  ],
  "comments": [
    {
      "id": 1362860,
      "author_name": "tomokikmogura",
      "author_url": "",
      "post_date": "06/23/2021 17:37:43",
      "content": "<p>Hi, <br>\nI think 4 target columns are not directly obtained from twitter's impression data because there are 2061 players but only 1447 twitter accounts in competition dataset. However, players who have twitter account tends to have higher <code>target*</code> value, therefore twitter activity probably have deep relation with <code>target*</code> values. See following short notebook if you are intereseted in!<br>\n<a href=\"https://www.kaggle.com/tomokikmogura/do-all-players-have-twitter-account?scriptVersionId=66455508\" target=\"_blank\">https://www.kaggle.com/tomokikmogura/do-all-players-have-twitter-account?scriptVersionId=66455508</a></p>",
      "votes": null,
      "replies": []
    },
    {
      "id": 1362881,
      "author_name": "mlconsult",
      "author_url": "",
      "post_date": "06/23/2021 17:58:56",
      "content": "<p>That is my thought as well… see this discussion</p>\n<p><a href=\"https://www.kaggle.com/c/mlb-player-digital-engagement-forecasting/discussion/246499\" target=\"_blank\">https://www.kaggle.com/c/mlb-player-digital-engagement-forecasting/discussion/246499</a></p>",
      "votes": null,
      "replies": []
    },
    {
      "id": 1363135,
      "author_name": "crained",
      "author_url": "",
      "post_date": "06/24/2021 00:17:34",
      "content": "<p>I was thinking the same. Seems like it does tie nicely to Twitter data. </p>",
      "votes": null,
      "replies": []
    },
    {
      "id": 1363173,
      "author_name": "mrigendraagrawal",
      "author_url": "",
      "post_date": "06/24/2021 01:54:49",
      "content": "<p>seems like that. after some analysis, I  found out targets are also somewhat correlated to each other looks like twitter gonna be an important feature</p>",
      "votes": null,
      "replies": []
    },
    {
      "id": 1363238,
      "author_name": "mlconsult",
      "author_url": "",
      "post_date": "06/24/2021 03:53:28",
      "content": "<p>The notebook below takes Mike Trouts tweets from February 2021 to the beginning of May and scales the 4 twitter metrics (retweets, likes, quotes and replies) between 0 and 100 just like the targets - it then plots the different metrics and Mike Trouts targets, from the MLB data, for the same period - after this I  do not think that the targets are the twitter metrics based on this analysis.</p>\n<p><a href=\"https://www.kaggle.com/mlconsult/twitter-data-compare\" target=\"_blank\">https://www.kaggle.com/mlconsult/twitter-data-compare</a></p>",
      "votes": null,
      "replies": []
    },
    {
      "id": 1364211,
      "author_name": "chetan8007",
      "author_url": "",
      "post_date": "06/24/2021 17:54:44",
      "content": "<p>thanks for sharing !</p>",
      "votes": null,
      "replies": []
    }
  ],
  "raw_markdown_by_id": {
    "1362817": "I am trying to figure out what target 1-4 is in the [previous](https://www.kaggle.com/c/mlb-player-digital-engagement-forecasting/discussion/247111) topic a few suggested that it might be twitter impression data.\n\nLooks like it could be predictions of following features of impression on a tweet.\n\n1. Number of comment\n2. Number of retweet\n3. Number of likes\n4. Number of shares\n\nOr is it a coincidence that we are predicting 4 targets and a tweet has exactly 4 measures of impressions on a tweet?",
    "1362860": "Hi, \nI think 4 target columns are not directly obtained from twitter's impression data because there are 2061 players but only 1447 twitter accounts in competition dataset. However, players who have twitter account tends to have higher `target*` value, therefore twitter activity probably have deep relation with `target*` values. See following short notebook if you are intereseted in!\nhttps://www.kaggle.com/tomokikmogura/do-all-players-have-twitter-account?scriptVersionId=66455508",
    "1362881": "That is my thought as well... see this discussion\n\nhttps://www.kaggle.com/c/mlb-player-digital-engagement-forecasting/discussion/246499",
    "1363135": "I was thinking the same. Seems like it does tie nicely to Twitter data.",
    "1363173": "seems like that. after some analysis, I  found out targets are also somewhat correlated to each other looks like twitter gonna be an important feature",
    "1363238": "The notebook below takes Mike Trouts tweets from February 2021 to the beginning of May and scales the 4 twitter metrics (retweets, likes, quotes and replies) between 0 and 100 just like the targets - it then plots the different metrics and Mike Trouts targets, from the MLB data, for the same period - after this I  do not think that the targets are the twitter metrics based on this analysis.\n\nhttps://www.kaggle.com/mlconsult/twitter-data-compare",
    "1364211": "thanks for sharing !"
  },
  "source": "meta"
}