{
  "fetched_at": "2026-10-19T22:31:47Z",
  "source_url": "https://www.kaggle.com/competitions/digital-banking-apps-reviews-classification/data",
  "pages": [
    {
      "name": "data-description",
      "content": "This competition provides three files, described as follows:\n\n## Files\n*   **train.csv** - The training data for training the model, with a total of 22,031 entries. Please refer to the explanation below for column descriptions.\n*   **test.csv** - The test data consists of approximately 9,443 entries, of which 4,773 are for the Public leaderboard, and 4,670 are for the Private leaderboard.\n*   **sample_submission.csv** - A sample submission file in the correct format.\n\n## Columns\n*   `index` - The serial number of the comment.\n*   `name` - The nickname of the customer on Google Play.\n*   `score` - The rating score.\n*   `dtm` - The time of the comment.\n*   `text` - The content of the comment.\n*   `app_name` - The name of the app.",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Description",
      "content": "There are many application scenarios for text classification technology in the company. Whether it’s in customer service, risk management, or investment domains, building text classification models can help companies automate processes and thus save a significant amount of labor costs. When we want to build a text classification model, we must first convert unstructured text into text features that the model can use. The key to the model’s effectiveness lies in the way text features are processed. In this event, we will take as an example the 30,000 comments data from 19 banking applications on Google Play. We will delve into different methods of processing text features, including term frequency matrices, TF-IDF, word2vec, large language models, and fine-tuning large language models, to compare their respective advantages and disadvantages as well as the differences in subsequent model effectiveness.\n\nThe data for this competition consists of approximately 30,000 review entries from 19 banks in Taiwan on their Google Play apps. You can try as many approaches as possible and upload your predictions through machine learning/deep learning models on the day of the event, which is on Saturday, 6/22.",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Evaluation",
      "content": "Although in practice, it is necessary to set different costs for errors depending on the situation, to simplify the content of this event, this competition will use [Accuracy](https://scikit-learn.org/stable/modules/generated/sklearn.metrics.accuracy_score.html) as the final evaluation metric.\n\n## Submission File\nThe uploaded data should contain two fields, namely index and pred, which represent the model’s prediction of the number of stars for the comment rating.\n```\nindex, pred\n2,1 顆星\n5,2 顆星\n6,3 顆星\netc.\n```",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "rules",
      "content": " - Don't cheat!\n - Apply yourself!\n - Have fun!",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "abstract",
      "content": "In this Kaggle competition, you will build a text classification model using comment data from 19 digital banking apps on the Google Play website. The model will predict the satisfaction scores of the comments, which range from 1 to 5. You can employ various methods for processing text features or different machine learning models, or a combination of both, to accurately predict the satisfaction scores reflected in the comments.",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    }
  ]
}