# DataScience1718@L3S — Data

来源：https://www.kaggle.com/competitions/ds1718l3s/data

本地 Meta Kaggle 快照；不是本次实时页面。

# Dataset Description

<p>In this task, you are given a set of text messages, your goal is to identify which are spam messages. There is no pre-defined criteria of what is a spam message, you have to explore in the training dataset based on the given label.</p>
<p>This task uses a real, public and non-encoded SMS spam collection [1] that is publicly available at: [https://archive.ics.uci.edu/ml/datasets/sms+spam+collection][1]. </p>

<h2>File descriptions</h2>
<ul>
<li><strong>train.tsv</strong> - the training set, contains 3000 rows and 2 columns (''label'' and ''content''), <strong>tab</strong> delimited </li>
<li><strong>test.tsv</strong> - the test set, contains 2574 rows and 2 columns (''id'' and ''content''), <strong>tab</strong> delimited</li>
<li><strong>sampleSubmission.csv</strong> - a sample submission file in the correct format, contains 2574 rows and 2 columns (''id'' and ''label''), <strong>comma</strong> delimited</li>
</ul>
<h2>Data fields</h2>
<ul>
<li><strong>id</strong> - an id unique to a given test case, i.e. a text message</li>
<li><strong>label</strong> - the label of a message indicates whether or not it is a spam message (1 - a spam message, 0 - not a spam message)</li>
<li><strong>content</strong> - the content of a text message</li>
</ul>

<p>[1] Almeida, Tiago A., José María G. Hidalgo, and Akebo Yamakami. "Contributions to the study of SMS spam filtering: new collection and results." In Proceedings of the 11th ACM symposium on Document engineering, pp. 259-262. ACM, 2011.</p>
  [1]: https://archive.ics.uci.edu/ml/datasets/sms+spam+collection