{
  "fetched_at": "2026-10-20T03:11:31Z",
  "source_url": "https://www.kaggle.com/competitions/ct5120suggestionmining/data",
  "pages": [
    {
      "name": "data-description",
      "content": "You will work with the data from SemEval-2019 Task 9 subtask A to classify whether a piece of text contains a suggestion or not.\n\n## Files\n\n*   **train.csv** - the training set\n*   **dev.csv** - the test set\n*   **test_no_label.csv** - the test set\n\n*   **sample_submission.csv** - a sample submission file in the correct format\n## Columns\n\n*   `id` - unique identifier for each sample\n*   `text` - text for each sample\n*   `label` - label for each sample (1 means suggestion and 0 is not)",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Description",
      "content": "This is an in-class competition for 2022-CT5120: Intro to NLP. We provide three training splits:\n1. train.csv: contains training data\n2. dev.csv: contains validation data\n3. test.csv: contains test data\n\nThis is a binary classification problem whereby participants should develop a supervised classification model that could classify if the given test sample is suggestion or not suggestion. Suggestions could be implicit or explicit whereby an author could recommend, request or suggest directly or indirectly. \n\nThe Competition leaderboard has two parts.\n\nThe public leaderboard provides publicly visible submission scores based on a representative sample of the test data. This leaderboard is visible throughout the competition.\n\nThe private leaderboard, by contrast, tracks model performance using the remainder of the test data. The private leaderboard thus has final say on whose models are best, and hence, who the winners and losers of the Competition will be. Which subset of data is calculated on the private leaderboard or a submission’s performance on the private leaderboard is not released to users until the competition has been closed.\n\nMany users watch the public leaderboard closely, as breakthroughs in the competition are announced by score gains in the leaderboard. These jumps in turn motivate other teams working on the competition in search of those advancements. But it’s important to keep the public leaderboard in perspective. It’s very easy to overfit a model, creating something that performs very well on the public leaderboard, but very badly on the private one. This is called overfitting.\n\n\n## Reference\nWe used the dataset provided in the SemEval-2019 Task 9: Suggestion Mining from Online Reviews and Forums\n\nSapna Negi, Tobias Daudert, and Paul Buitelaar. 2019. SemEval-2019 Task 9: Suggestion Mining from Online Reviews and Forums. In Proceedings of the 13th International Workshop on Semantic Evaluation, pages 877–887, Minneapolis, Minnesota, USA. Association for Computational Linguistics",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Evaluation",
      "content": "The evaluation pages describes how submissions will be scored and how students should format their submissions. You don't need a sub-title at the top; the page title appears above. For an example of a high quality evaluation page, see the 2013 KDD Cup page, which we have included below:\n\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\n## Submission Format\n\nSubmission files should contain two columns: `Id` and `Expected`. `Expected` should either 1 (if suggestion)or 0 (if not). `Id` is a unique identifier given in the `test.csv` ranges from *test_0 to test_1699*.  `Id` and `Expected` values should be separated by `,`\n\nUse `StudentID_Lastname.csv` as filename while submitting\n\nThe file should contain a header and have the following format:\n```\nId,Expected\ntest_0,1\ntest_1,0\n```  ",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "rules",
      "content": "Participants are allowed to submit 3 submissions in a day. However, the latest two would be considered for final evaluation, and the once with the highest evaluation score would be selected for the leaderboard.\n\nThe public leaderboard provides publicly visible submission scores based on a representative sample of the test data. This leaderboard is visible throughout the competition.\n\nThe private leaderboard, by contrast, tracks model performance using the remainder of the test data. The private leaderboard thus has final say on whose models are best, and hence, who the winners and losers of the Competition will be.\n\nPrivate leaderboard score would be published after the deadline.",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    }
  ]
}