# Demo - News Popularity Prediction — Data

来源：https://www.kaggle.com/competitions/demolab-news-popularity-prediction/data

采集时间：2026-10-24T17:00:45Z

# File descriptions:
`train.csv:` Contains 61 columns. The primary key that represents each new article is id. The target variable that you need to predict is `shares` which contains a continuous value (integer). This data is what you are going to use for EDA, cleaning, feature engineering, model building, model evaluation, model selection, and finally model training.

`test.csv:` Contains 60 columns, doesn't contain the target variable `shares`. You will apply all the necessary preprocessing steps to get this data into the right format and then use the model trained using the `train.csv` file to make predictions with this. This is unseen data! Only the competition hosts know the actual values of the target feature for this data and therefore your submissions will be evaluated on how well your model does with this dataset.

`sample.csv:` This contains the format in which you need to submit the solutions to Kaggle. The id column in this dataset exactly the same as the id column in `test.csv`. You will make your predictions on the `test.csv` data and store them in a submission file that has the same format as this file. Check the `Overview>Evaluation` tab for mode details.

`data_dictionary.csv:` This contains the definitions for the various columns/features that you will need for the modeling exercise. This competition provides some numeric features for each of the articles and their metadata, as well as some features extracted by different models such as topic models (LDA), sentiment analysis models, subjectivity analysis models etc.

---------

# Dataset 
This dataset summarizes a heterogeneous set of features about articles published by Mashable in a period of two years. The goal is to predict the number of shares in social networks (popularity). The features provided to you broadly come from 5 areas - 

1. Word features: Features that summarize statistics about the words being used in the article
2. Links & References features: Features that summarize the statistics about the links and references being used in the article
3. Digital Media features: Features that include information about the images and videos in the article.
4. Temporal features: Time-based features related to when the article was published.
5. Keyword features: Features that talk about the keywords (hashtags for an article) and categories (data channels) associated with the article (e.g. arts, science etc)
6. NLP features: Features that come from a variety of models that were run on the articles, including Topic models (LDA), Sentiment analysis models, Subjectivity analysis models etc.

![features](https://i.imgur.com/BBm7VLQ.png)

>Note:
>
>1. Detailed definitions for each of the variables are provided in the `data_dictionary.csv`
>
>2. The starter notebook will also help guide you on how to work with the features provided.