PAN20 Authorship Analysis: Celebrity Profiling

<strong>Synopsis</strong> Task: Given the Twitter feeds of the followers, determine the occupation, age, and gender of a celebrity. Evaluation: [code] Baselines: [code] See the full Shared Task [here] The datasets contain three files: a <code>follower-feeds.ndjson</code> as input, a <code>labels.ndjson</code> as output, and a <code>celebrity-feeds.ndjson</code> for additional study. Each file lists all celebrities as JSON objects, one per line and identified by the <code>id</code> key. The training dataset contains 1,920 celebrities and is balanced towards gender and occupation. The supplement dataset contains the remaining 8,265 celebrities but is not balanced in any way. The <code>follower-feeds.ndjson</code> contains the English tweets of at least 10 followers for each celebrity, with at least 50 tweets each excluding retweets. <pre><code class="language-json">{"id": 1234, "text": [["a tweet of follower 1", "another tweet of follower 1", ...], ["a tweet of follower 2", ...], ...]} {"id": 5678, "text": [["a tweet of follower 1", "another tweet of follower 1", ...], ["a tweet of follower 2", ...], ...]}</code></pre> The <code>celebrity-feeds.ndjson</code> contains the Twitter timelines of the original celebrities, formatted as: <pre><code class="language-json">{"id": 1234, "text": ["a tweet of celebrity 1", "another tweet of celebrity 1", ...]} {"id": 5678, "text": ["a tweet of celebrity 2", "another tweet", ...]}</code></pre> The <code>labels.ndjson</code> contains the classes that should be predicted. A valid submission has to produce a <code>labels.ndjson</code> given the <code>follower-feeds.ndjson</code> and contain an entry for each <code>id</code> given in the input. <pre><code class="language-json">{"id": 1234, "occupation": "sports", "gender": "female", "birthyear": 2002} {"id": 5678, "occupation": "professional", "gender": "male", "birthyear": 1990}</code></pre> The following values are possible for each of the traits: <pre><code>occupation := {sports, performer, creator, politics} birthyear := {1940, ..., 1999} gender := {male, female}</code></pre>任务概述 任务：基于名人粉丝的推特（Twitter）动态，预测该名人的职业、出生年份与性别。 评估方式：[代码块] 基线模型：[代码块] 完整共享任务详情请见[此处] 本数据集包含三个文件：作为输入的`follower-feeds.ndjson`、作为输出的`labels.ndjson`，以及用于辅助研究的`celebrity-feeds.ndjson`。所有文件均以JSON（JavaScript对象表示法）对象形式逐行列出所有名人，每个对象通过`id`字段进行唯一标识。 训练集包含1920位名人，其样本在性别与职业维度上均保持均衡分布。补充数据集包含剩余的8265位名人，未做任何均衡处理。 `follower-feeds.ndjson` 存储了每位名人至少10位粉丝的英文推特内容，每位粉丝的有效推文（不含转发）数量至少为50条。示例格式如下： json {"id": 1234, "text": [["a tweet of follower 1", "another tweet of follower 1", ...], ["a tweet of follower 2", ...], ...]} {"id": 5678, "text": [["a tweet of follower 1", "another tweet of follower 1", ...], ["a tweet of follower 2", ...], ...]} `celebrity-feeds.ndjson` 存储了原名人的推特时间线，格式如下： json {"id": 1234, "text": ["a tweet of celebrity 1", "another tweet of celebrity 1", ...]} {"id": 5678, "text": ["a tweet of celebrity 2", "another tweet", ...]} `labels.ndjson` 包含模型需预测的标签类别。合规的提交结果需基于`follower-feeds.ndjson`生成`labels.ndjson`，且需为输入文件中出现的每一个`id`生成一条对应条目。示例格式如下： json {"id": 1234, "occupation": "sports", "gender": "female", "birthyear": 2002} {"id": 5678, "occupation": "professional", "gender": "male", "birthyear": 1990} 各特征的可选取值如下： - 职业（occupation）：可选集合为{sports, performer, creator, politics}，对应中文类别为体育、演艺、创作者、政界 - 出生年份（birthyear）：可选范围为1940年至1999年的整数年份 - 性别（gender）：可选集合为{male, female}，对应中文类别为男、女