{
  "fetched_at": "2026-10-19T21:28:37Z",
  "source_url": "https://www.kaggle.com/competitions/clblp-task-2/data",
  "pages": [
    {
      "name": "data-description",
      "content": "Sentiment classification is a challenging research issue in a resource-poor language like Bengali. The inadequacy of the benchmark dataset and the limited amount of e-textual content or reviews in the Bengali language resulted in the sentiment classification task being more complicated. Moreover, in recent years people frequently using code-mixed or code-switched texts which is also a crucial concern for machine learning model developers.\n\n **For this competition,  we released a dataset comprised of around 8.5K code-mixed texts labeled in two sentiment categories: `Positive (1)`, and `Negative (0)`.** \n\n## Files\n\n*   **train.csv** - the training set\n*   **test.csv** - the test set\n*   **sample_submission.csv** - a sample submission file in the correct format\n\n\n## Columns\n\n*   `Id` - Unique Number\n*   `Reviews` - Bengali reviews\n*   `Sentiment` - Sentiment category either `0 or 1`",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Description",
      "content": "Sentiment detection is a computational technique that attempts to uncover the viewpoint of a user towards a specific entity. It aims to determine the contextual polarity of the text contents (such as comments, reviews, tweets, or posts) as positive or negative. Sentiment analysis has shown a remarkable impact on the business community, whereby taking into account the user opinions, the communities can ensure the sustainability of their product or services. The restaurant is one such business where customers' opinions can be utilized to improve the quality of food, environment, and services. To collect excellent services, customers' instinct is to look through the restaurant reviews before visiting it. Therefore, reviewing a restaurant via the internet has become an ecumenical trend. Thus, it is crucial to identify the sentiment of the user reviews to provide satisfactory services. Moreover, there is a broader business interest in developing a Bengali AI tool to identify sentiment from **code-mixed** (Bengali+English) texts. In this regard, we, **[CUET NLP Lab](https://cuetnlp.com/)**, are elated to present an **NLP competition**, as a part of the 2nd International Workshop on Computational Linguistics and Bangla Language Processing 2023.\n\nThis competition is open only to students. \nRegistration is required to participate in the competition.  [Registration Link](https://forms.gle/sse3t3xALCboYMJD9) \n\n**Last Date of Registration:** 10th February 2023\nFollow the Facebook event page for the updated information: [CLBLP 2023](https://fb.me/e/3a0ueBDL2)\n\n\n## Competition Information: \nThe Competition will be held from 13th February to 17th February 2023.\nParticipants abide to follow the competition Rules. Violation of any rules will lead to disqualifying the team from the competition.\n\n**Competition Prize Money: Announced Later**\n\n**Important**: All the teams have to publish their notebooks after the end of the competition period.\n\n\n\n\n## Reference\n\nThe following paper describes the process of developing a Bengali sentiment analysis framework.\n\n[Springer'20 Paper](https://link.springer.com/chapter/10.1007/978-3-030-73050-5_19)",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Evaluation",
      "content": "The evaluation metric for the competition is `Micro F1-Score`.\n\n## Submission Format\n\nThe submission files should contain two columns: `Id` and `Sentiment` where the Sentiment will be your model predictions (0 or 1) for the respective reviews. \n\nThe file should contain a header and have the following format:\n```\nId, Sentiment \n11, 1\n```",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "rules",
      "content": "Participants abide to go through the following rules before starting participation in this competition:\n\n - For the competition, only three members are allowed per team.\n - All teams have to submit their working Kaggle notebooks with appropriate\n    instructions.\n - Top three teams have to show their notebooks and models with an onsite light presentation.   \n - Submitted Notebooks having similarities with other team notebooks will lead to\n    discarding the teams from the competition.\n - The maximum number of submissions per team per day is 2.\n -  Competition Data: Data can be used for competition, academic, and non-commercial purposes only. No\n      external dataset is allowed. Manual labeling of the test dataset is prohibited and will lead to\n      disqualification.\n - You warrant that your submission is your own original work. In case of any incongruity, the\n      organizers serve the right to disqualify any team.\n - Winners will be selected based on the leaderboard score, notebooks quality, and at the sole\n      discretion of the Organizing Committee. All participants must conform to the terms and\n      conditions. The Committee’s decisions in this regard will be considered final.",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    }
  ]
}