tweets2013-ia dataset with TREC microblog 2013-14

#37
allenai · Mar 1, 2021 · 158a0e5 · 158a0e5
1 parent 7ef592b
commit 158a0e5
Show file tree

Hide file tree

Showing 12 changed files with 848 additions and 8 deletions.
diff --git a/.github/workflows/verify_downloads.yml b/.github/workflows/verify_downloads.yml
@@ -409,6 +409,24 @@ jobs:
       run: |
         python -m test.downloads --filter "^trec-spanish/"
 
+  tweets2013-ia:
+    runs-on: ubuntu-latest
+    steps:
+    - uses: actions/checkout@v2
+    - name: Set up Python
+      uses: actions/setup-python@v2
+      with:
+        python-version: '3.x'
+    - name: Install dependencies
+      run: |
+        python -m pip install --upgrade pip
+        pip install -r requirements.txt
+    - name: Test
+      env:
+        IR_DATASETS_DL_DISABLE_PBAR: 'true'
+      run: |
+        python -m test.downloads --filter "^tweets2013-ia/"
+
   vaswani:
     runs-on: ubuntu-latest
     steps:

diff --git a/README.md b/README.md
@@ -240,6 +240,7 @@ Available datasets include:
  - [TREC Mandarin](https://ir-datasets.com/trec-mandarin.html)
  - [TREC Robust 2004](https://ir-datasets.com/trec-robust04.html)
  - [TREC Spanish](https://ir-datasets.com/trec-spanish.html)
+ - [Tweets 2013 (Internet Archive)](https://ir-datasets.com/tweets2013-ia.html)
  - [Vaswani](https://ir-datasets.com/vaswani.html)
  - [WikIR](https://ir-datasets.com/wikir.html)
 

diff --git a/docs/master/index.html b/docs/master/index.html
@@ -195,6 +195,9 @@ <h2>Dataset Index</h2>
 </tbody><tbody><tr><td><a style="font-weight: bold;" href="trec-spanish.html"><kbd>trec-spanish</kbd></a></li></td><td class="center"><span style="cursor: help;" title="docs available from LDC">⚠️</span></td><td class="center"></td><td class="center"></td><td class="center screen-small-hide"></td><td class="center screen-small-hide"></td></tr>
 <tr><td><a href="trec-spanish.html#trec-spanish/trec3"><kbd><span class="prefix">trec-spanish</span>/trec3</kbd></a></td><td class="center"><span style="cursor: help;" title="docs available from LDC">⚠️</span></td><td class="center"><span style="cursor: help;" title="queries available as automatic download">✅</span></td><td class="center"><span style="cursor: help;" title="qrels available as automatic download">✅</span></td><td class="center screen-small-hide"></td><td class="center screen-small-hide"></td></tr>
 <tr><td><a href="trec-spanish.html#trec-spanish/trec4"><kbd><span class="prefix">trec-spanish</span>/trec4</kbd></a></td><td class="center"><span style="cursor: help;" title="docs available from LDC">⚠️</span></td><td class="center"><span style="cursor: help;" title="queries available as automatic download">✅</span></td><td class="center"><span style="cursor: help;" title="qrels available as automatic download">✅</span></td><td class="center screen-small-hide"></td><td class="center screen-small-hide"></td></tr>
+</tbody><tbody><tr><td><a style="font-weight: bold;" href="tweets2013-ia.html"><kbd>tweets2013-ia</kbd></a></li></td><td class="center"><span style="cursor: help;" title="docs available as automatic download">✅</span></td><td class="center"></td><td class="center"></td><td class="center screen-small-hide"></td><td class="center screen-small-hide"></td></tr>
+<tr><td><a href="tweets2013-ia.html#tweets2013-ia/trec-mb-2013"><kbd><span class="prefix">tweets2013-ia</span>/trec-mb-2013</kbd></a></td><td class="center"><span style="cursor: help;" title="docs available as automatic download">✅</span></td><td class="center"><span style="cursor: help;" title="queries available as automatic download">✅</span></td><td class="center"><span style="cursor: help;" title="qrels available as automatic download">✅</span></td><td class="center screen-small-hide"></td><td class="center screen-small-hide"></td></tr>
+<tr><td><a href="tweets2013-ia.html#tweets2013-ia/trec-mb-2014"><kbd><span class="prefix">tweets2013-ia</span>/trec-mb-2014</kbd></a></td><td class="center"><span style="cursor: help;" title="docs available as automatic download">✅</span></td><td class="center"><span style="cursor: help;" title="queries available as automatic download">✅</span></td><td class="center"><span style="cursor: help;" title="qrels available as automatic download">✅</span></td><td class="center screen-small-hide"></td><td class="center screen-small-hide"></td></tr>
 </tbody><tbody><tr><td><a style="font-weight: bold;" href="vaswani.html"><kbd>vaswani</kbd></a></li></td><td class="center"><span style="cursor: help;" title="docs available as automatic download">✅</span></td><td class="center"><span style="cursor: help;" title="queries available as automatic download">✅</span></td><td class="center"><span style="cursor: help;" title="qrels available as automatic download">✅</span></td><td class="center screen-small-hide"></td><td class="center screen-small-hide"></td></tr>
 </tbody><tbody><tr><td><a style="font-weight: bold;" href="wikir.html"><kbd>wikir</kbd></a></li></td><td class="center"></td><td class="center"></td><td class="center"></td><td class="center screen-small-hide"></td><td class="center screen-small-hide"></td></tr>
 <tr><td><a href="wikir.html#wikir/en1k"><kbd><span class="prefix">wikir</span>/en1k</kbd></a></td><td class="center"><span style="cursor: help;" title="docs available as automatic download">✅</span></td><td class="center"></td><td class="center"></td><td class="center screen-small-hide"></td><td class="center screen-small-hide"></td></tr>

diff --git a/docs/master/tweets2013-ia.html b/docs/master/tweets2013-ia.html
@@ -0,0 +1,244 @@
+<!DOCTYPE html>
+<html>
+<head>
+<link rel="stylesheet" href="main.css" />
+<script src="https://code.jquery.com/jquery-1.12.4.min.js" integrity="sha256-ZosEbRLbNQzLpnKIkEdrPv7lOy9C27hHQ+Xp8a4MxAQ=" crossorigin="anonymous"></script>
+<script src="https://code.jquery.com/ui/1.12.1/jquery-ui.min.js" integrity="sha256-VazP97ZCwtekAsvgPBSUwPFKdrwD3unUfSGVYrahUqU=" crossorigin="anonymous"></script>
+<script src="main.js"></script>
+<meta charset="utf-8" />
+<meta name="viewport" content="width=device-width, initial-scale=1" />
+<meta name="robots" content="noindex,nofollow" />
+<title>Tweets 2013 (Internet Archive) - ir_datasets</title>
+<body>
+<div class="page">
+
+<div class="banner">This documentation is for <strong>master</strong>. See <a href="../tweets2013-ia.html">here</a> for documentation of the current latest version on pypi.</div>
+
+<div style="position: absolute; top: 4px; left: 4px;"><a href="index.html">&larr; home</a></div>
+
+<div style="position: absolute; top: 4px; right: 4px;">Github: <a href="https://github.com/allenai/ir_datasets/blob/master/ir_datasets/datasets/tweets2013_ia.py">datasets/tweets2013_ia.py</a></div>
+<h1><code>ir_datasets</code>: Tweets 2013 (Internet Archive)</h1>
+<div style="font-weight: bold; font-size: 1.1em;">Index</div>
+<ol class="index">
+<li><a href="#tweets2013-ia"><kbd>tweets2013-ia</kbd></a></li>
+<li><a href="#tweets2013-ia/trec-mb-2013"><kbd><span class="prefix">tweets2013-ia</span>/trec-mb-2013</kbd></a></li>
+<li><a href="#tweets2013-ia/trec-mb-2014"><kbd><span class="prefix">tweets2013-ia</span>/trec-mb-2014</kbd></a></li>
+</ol>
+<hr />
+<div class="dataset" id="tweets2013-ia">
+<h3><kbd class="select"><span class="str">"tweets2013-ia"</kdb></h3>
+
+<div class="desc">
+ <p> A collection of tweets from a 2-month window achived by the Internet Achive. This collection can be a stand-in document collection for the TREC Microblog 2013-14 tasks. (Even though it is not exactly the same collection, <a href="https://cs.uwaterloo.ca/~jimmylin/publications/Sequiera_Lin_SIGIR2017.pdf">Sequiera and Lin</a> show that it it close enough.) </p> <p> This collection is automatically downloaded from the Internet Archive, though download speeds are often slow so it takes some time. ir_datasets constructs a new directory hierarchy during the download process to facilitate fast lookups and slices. </p> <ul> <li>Documents: Tweets</li> <li><a href="https://cs.uwaterloo.ca/~jimmylin/publications/Sequiera_Lin_SIGIR2017.pdf">Information about dataset (paper)</a></li> <li><a href="https://github.com/castorini/Tweets2013-IA">Information about dataset (repository)</a></li> </ul>
+</div>
+<div class="tabs">
+<a class="tab" target="tweets2013-ia__docs">docs</a>
+<div id="tweets2013-ia__docs" class="tab-content">
+<p>Language: <em>multiple/other/unknown</em></p>
+<div>Document type:</div>
+<div class="type">
+<div class="type-name">TweetDoc: (<span class="kwd">namedtuple</span>)</div>
+<ol class="type-fields">
+<li data-tuple-idx="0"><span class="">doc_id</span>: <span class="kwd">str</span></li><li data-tuple-idx="1"><span class="">text</span>: <span class="kwd">str</span></li><li data-tuple-idx="2"><span class="">user_id</span>: <span class="kwd">str</span></li><li data-tuple-idx="3"><span class="">created_at</span>: <span class="kwd">str</span></li><li data-tuple-idx="4"><span class="">lang</span>: <span class="kwd">str</span></li><li data-tuple-idx="5"><span class="">reply_doc_id</span>: <span class="kwd">str</span></li><li data-tuple-idx="6"><span class="">retweet_doc_id</span>: <span class="kwd">str</span></li><li data-tuple-idx="7"><span class="">source</span>: <span class="kwd">bytes</span></li><li data-tuple-idx="8"><span class="">source_content_type</span>: <span class="kwd">str</span></li>
+</ol>
+</div>
+<p>Example</p>
+<code class="example">
+<div><span class="kwd">import</span> ir_datasets</div>
+<div>dataset = ir_datasets.load(<span class="str">'tweets2013-ia')</div>
+<div><span class="kwd">for</span> doc <span class="kwd">in</span> dataset.docs_iter():</div>
+<div>&nbsp;&nbsp;&nbsp;&nbsp;doc <span class="comment"># namedtuple&lt;doc_id, text, user_id, created_at, lang, reply_doc_id, retweet_doc_id, source, source_content_type&gt;</span></div>
+</code>
+</div>
+
+<a class="tab" target="tweets2013-ia__citation">Citation</a>
+<div id="tweets2013-ia__citation" class="tab-content">
+bibtex:
+<cite class="select">@inproceedings{Sequiera2017Finally,
+  title={Finally, a Downloadable Test Collection of Tweets},
+  author={Royal Sequiera and Jimmy Lin},
+  booktitle={SIGIR},
+  year={2017}
+}
+</cite>
+</div>
+</div>
+</div>
+
+<hr />
+<div class="dataset" id="tweets2013-ia/trec-mb-2013" data-parent="tweets2013-ia">
+<h3><kbd class="ds-name select"><span class="str">"tweets2013-ia/trec-mb-2013"</kdb></h3>
+
+<div class="desc">
+ <p> TREC Microblog 2013 test collection. </p> <ul> <li><a href="https://trec.nist.gov/pubs/trec22/papers/MB.OVERVIEW.pdf">Shared Task Paper</a></li> <li><a href="https://github.com/lintool/twitter-tools/wiki/TREC-2013-Track-Guidelines">Shared Task Site</a></li> </ul> 
+</div>
+<div class="tabs">
+<a class="tab" target="tweets2013-ia/trec-mb-2013__queries">queries</a>
+<div id="tweets2013-ia/trec-mb-2013__queries" class="tab-content">
+<p>Language: <span class="lang-code">en</span></p>
+<div>Query type:</div>
+<div class="type">
+<div class="type-name">TrecMb13Query: (<span class="kwd">namedtuple</span>)</div>
+<ol class="type-fields">
+<li data-tuple-idx="0"><span class="">query_id</span>: <span class="kwd">str</span></li><li data-tuple-idx="1"><span class="">query</span>: <span class="kwd">str</span></li><li data-tuple-idx="2"><span class="">time</span>: <span class="kwd">str</span></li><li data-tuple-idx="3"><span class="">tweet_time</span>: <span class="kwd">str</span></li>
+</ol>
+</div>
+<p>Example</p>
+<code class="example">
+<div><span class="kwd">import</span> ir_datasets</div>
+<div>dataset = ir_datasets.load(<span class="str">'tweets2013-ia/trec-mb-2013')</div>
+<div><span class="kwd">for</span> query <span class="kwd">in</span> dataset.queries_iter():</div>
+<div>&nbsp;&nbsp;&nbsp;&nbsp;query <span class="comment"># namedtuple&lt;query_id, query, time, tweet_time&gt;</span></div>
+</code>
+</div>
+
+<a class="tab" target="tweets2013-ia/trec-mb-2013__docs">docs</a>
+<div id="tweets2013-ia/trec-mb-2013__docs" class="tab-content">
+<p>Language: <em>multiple/other/unknown</em></p>
+<div>Document type:</div>
+<div class="type">
+<div class="type-name">TweetDoc: (<span class="kwd">namedtuple</span>)</div>
+<ol class="type-fields">
+<li data-tuple-idx="0"><span class="">doc_id</span>: <span class="kwd">str</span></li><li data-tuple-idx="1"><span class="">text</span>: <span class="kwd">str</span></li><li data-tuple-idx="2"><span class="">user_id</span>: <span class="kwd">str</span></li><li data-tuple-idx="3"><span class="">created_at</span>: <span class="kwd">str</span></li><li data-tuple-idx="4"><span class="">lang</span>: <span class="kwd">str</span></li><li data-tuple-idx="5"><span class="">reply_doc_id</span>: <span class="kwd">str</span></li><li data-tuple-idx="6"><span class="">retweet_doc_id</span>: <span class="kwd">str</span></li><li data-tuple-idx="7"><span class="">source</span>: <span class="kwd">bytes</span></li><li data-tuple-idx="8"><span class="">source_content_type</span>: <span class="kwd">str</span></li>
+</ol>
+</div>
+<p>Example</p>
+<code class="example">
+<div><span class="kwd">import</span> ir_datasets</div>
+<div>dataset = ir_datasets.load(<span class="str">'tweets2013-ia/trec-mb-2013')</div>
+<div><span class="kwd">for</span> doc <span class="kwd">in</span> dataset.docs_iter():</div>
+<div>&nbsp;&nbsp;&nbsp;&nbsp;doc <span class="comment"># namedtuple&lt;doc_id, text, user_id, created_at, lang, reply_doc_id, retweet_doc_id, source, source_content_type&gt;</span></div>
+</code>
+</div>
+
+<a class="tab" target="tweets2013-ia/trec-mb-2013__qrels">qrels</a>
+<div id="tweets2013-ia/trec-mb-2013__qrels" class="tab-content">
+<div>Query relevance judgment type:</div>
+<div class="type">
+<div class="type-name">TrecQrel: (<span class="kwd">namedtuple</span>)</div>
+<ol class="type-fields">
+<li data-tuple-idx="0"><span class="">query_id</span>: <span class="kwd">str</span></li><li data-tuple-idx="1"><span class="">doc_id</span>: <span class="kwd">str</span></li><li data-tuple-idx="2"><span class="">relevance</span>: <span class="kwd">int</span></li><li data-tuple-idx="3"><span class="">iteration</span>: <span class="kwd">str</span></li>
+</ol>
+</div>
+<p>Relevance levels</p>
+
+<table>
+<tr><th>Rel.</th><th>Definition</th></tr>
+<tr><td class="relScore">0</td><td>not relevant</td></tr>
+<tr><td class="relScore">1</td><td>relevant</td></tr>
+<tr><td class="relScore">2</td><td>highly relevant</td></tr>
+</table>
+
+<p>Example</p>
+<code class="example">
+<div><span class="kwd">import</span> ir_datasets</div>
+<div>dataset = ir_datasets.load(<span class="str">'tweets2013-ia/trec-mb-2013')</div>
+<div><span class="kwd">for</span> qrel <span class="kwd">in</span> dataset.qrels_iter():</div>
+<div>&nbsp;&nbsp;&nbsp;&nbsp;qrel <span class="comment"># namedtuple&lt;query_id, doc_id, relevance, iteration&gt;</span></div>
+</code>
+</div>
+
+<a class="tab" target="tweets2013-ia/trec-mb-2013__citation">Citation</a>
+<div id="tweets2013-ia/trec-mb-2013__citation" class="tab-content">
+bibtex:
+<cite class="select">@inproceedings{Lin2013Microblog,
+  title={Overview of the TREC-2013 Microblog Track},
+  author={Jimmy Lin and Miles Efron},
+  booktitle={TREC},
+  year={2013}
+}
+</cite>
+</div>
+</div>
+</div>
+
+<hr />
+<div class="dataset" id="tweets2013-ia/trec-mb-2014" data-parent="tweets2013-ia">
+<h3><kbd class="ds-name select"><span class="str">"tweets2013-ia/trec-mb-2014"</kdb></h3>
+
+<div class="desc">
+ <p> TREC Microblog 2014 test collection. </p> <ul> <li><a href="https://trec.nist.gov/pubs/trec23/papers/overview-microblog.pdf">Shared Task Paper</a></li> <li><a href="https://github.com/lintool/twitter-tools/wiki/TREC-2014-Track-Guidelines">Shared Task Site</a></li> </ul> 
+</div>
+<div class="tabs">
+<a class="tab" target="tweets2013-ia/trec-mb-2014__queries">queries</a>
+<div id="tweets2013-ia/trec-mb-2014__queries" class="tab-content">
+<p>Language: <span class="lang-code">en</span></p>
+<div>Query type:</div>
+<div class="type">
+<div class="type-name">TrecMb14Query: (<span class="kwd">namedtuple</span>)</div>
+<ol class="type-fields">
+<li data-tuple-idx="0"><span class="">query_id</span>: <span class="kwd">str</span></li><li data-tuple-idx="1"><span class="">query</span>: <span class="kwd">str</span></li><li data-tuple-idx="2"><span class="">time</span>: <span class="kwd">str</span></li><li data-tuple-idx="3"><span class="">tweet_time</span>: <span class="kwd">str</span></li><li data-tuple-idx="4"><span class="">description</span>: <span class="kwd">str</span></li>
+</ol>
+</div>
+<p>Example</p>
+<code class="example">
+<div><span class="kwd">import</span> ir_datasets</div>
+<div>dataset = ir_datasets.load(<span class="str">'tweets2013-ia/trec-mb-2014')</div>
+<div><span class="kwd">for</span> query <span class="kwd">in</span> dataset.queries_iter():</div>
+<div>&nbsp;&nbsp;&nbsp;&nbsp;query <span class="comment"># namedtuple&lt;query_id, query, time, tweet_time, description&gt;</span></div>
+</code>
+</div>
+
+<a class="tab" target="tweets2013-ia/trec-mb-2014__docs">docs</a>
+<div id="tweets2013-ia/trec-mb-2014__docs" class="tab-content">
+<p>Language: <em>multiple/other/unknown</em></p>
+<div>Document type:</div>
+<div class="type">
+<div class="type-name">TweetDoc: (<span class="kwd">namedtuple</span>)</div>
+<ol class="type-fields">
+<li data-tuple-idx="0"><span class="">doc_id</span>: <span class="kwd">str</span></li><li data-tuple-idx="1"><span class="">text</span>: <span class="kwd">str</span></li><li data-tuple-idx="2"><span class="">user_id</span>: <span class="kwd">str</span></li><li data-tuple-idx="3"><span class="">created_at</span>: <span class="kwd">str</span></li><li data-tuple-idx="4"><span class="">lang</span>: <span class="kwd">str</span></li><li data-tuple-idx="5"><span class="">reply_doc_id</span>: <span class="kwd">str</span></li><li data-tuple-idx="6"><span class="">retweet_doc_id</span>: <span class="kwd">str</span></li><li data-tuple-idx="7"><span class="">source</span>: <span class="kwd">bytes</span></li><li data-tuple-idx="8"><span class="">source_content_type</span>: <span class="kwd">str</span></li>
+</ol>
+</div>
+<p>Example</p>
+<code class="example">
+<div><span class="kwd">import</span> ir_datasets</div>
+<div>dataset = ir_datasets.load(<span class="str">'tweets2013-ia/trec-mb-2014')</div>
+<div><span class="kwd">for</span> doc <span class="kwd">in</span> dataset.docs_iter():</div>
+<div>&nbsp;&nbsp;&nbsp;&nbsp;doc <span class="comment"># namedtuple&lt;doc_id, text, user_id, created_at, lang, reply_doc_id, retweet_doc_id, source, source_content_type&gt;</span></div>
+</code>
+</div>
+
+<a class="tab" target="tweets2013-ia/trec-mb-2014__qrels">qrels</a>
+<div id="tweets2013-ia/trec-mb-2014__qrels" class="tab-content">
+<div>Query relevance judgment type:</div>
+<div class="type">
+<div class="type-name">TrecQrel: (<span class="kwd">namedtuple</span>)</div>
+<ol class="type-fields">
+<li data-tuple-idx="0"><span class="">query_id</span>: <span class="kwd">str</span></li><li data-tuple-idx="1"><span class="">doc_id</span>: <span class="kwd">str</span></li><li data-tuple-idx="2"><span class="">relevance</span>: <span class="kwd">int</span></li><li data-tuple-idx="3"><span class="">iteration</span>: <span class="kwd">str</span></li>
+</ol>
+</div>
+<p>Relevance levels</p>
+
+<table>
+<tr><th>Rel.</th><th>Definition</th></tr>
+<tr><td class="relScore">0</td><td>not relevant</td></tr>
+<tr><td class="relScore">1</td><td>relevant</td></tr>
+<tr><td class="relScore">2</td><td>highly relevant</td></tr>
+</table>
+
+<p>Example</p>
+<code class="example">
+<div><span class="kwd">import</span> ir_datasets</div>
+<div>dataset = ir_datasets.load(<span class="str">'tweets2013-ia/trec-mb-2014')</div>
+<div><span class="kwd">for</span> qrel <span class="kwd">in</span> dataset.qrels_iter():</div>
+<div>&nbsp;&nbsp;&nbsp;&nbsp;qrel <span class="comment"># namedtuple&lt;query_id, doc_id, relevance, iteration&gt;</span></div>
+</code>
+</div>
+
+<a class="tab" target="tweets2013-ia/trec-mb-2014__citation">Citation</a>
+<div id="tweets2013-ia/trec-mb-2014__citation" class="tab-content">
+bibtex:
+<cite class="select">@inproceedings{Lin2014Microblog,
+  title={Overview of the TREC-2014 Microblog Track},
+  author={Jimmy Lin and Miles Efron and Yulu Wang and Garrick Sherman},
+  booktitle={TREC},
+  year={2014}
+}
+</cite>
+</div>
+</div>
+</div>
+
+</div>
+</body>
+</html>
diff --git a/ir_datasets/datasets/__init__.py b/ir_datasets/datasets/__init__.py
@@ -21,5 +21,6 @@
 from . import trec_arabic
 from . import trec_mandarin
 from . import trec_spanish
+from . import tweets2013_ia
 from . import vaswani
 from . import wikir