地球资源数据云——数据资源详情
垃圾邮件 URL 分类数据集
该数据集《Spam URLs Classification Dataset》主要用于二分类任务，数据形态以文本为主，应用场景偏向金融风控。 题目说明：Classification of a URL if spam or not spam 任务类型：文本二分类。 建议流程：先做文本清洗与分词，再比较 TF - IDF+线性模型 与 预训练语言模型。 评估建议：使用分层切分或交叉验证，优先关注 F1、Recall、AUC 等分类指标。 可用文件：url_spam_classification.csv。 URL - Spam or Not Spam - Classification Dataset This dataset contains about 87.5K URLs in which one - third are flagged as a spam URL and restrict are not spam. It can be used to create a binary classification model. Credits: The dataset was created by The Pudding. This dataset of every link is found in different newsletters. The flagging system identifies if a link is a spam or not, as it parses links from over 100 newsletters every 30 minutes. A link is programatically f flagged if it appears 3+ times in a single newsletter or contains a likely subscribe/unsubscribe URL. If you use this dataset, don't forget to cite the author.
摘要概览
该数据集《Spam URLs Classification Dataset》主要用于二分类任务，数据形态以文本为主，应用场景偏向金融风控。 题目说明：Classification of a URL if spam or not spam
任务类型：文本二分类。
建议流程：先做文本清洗与分词，再比较 TF - IDF+线性模型 与 预训练语言模型。
评估建议：使用分层切分或交叉验证，优先关注 F1、Recall、AUC 等分类指标。
可用文件：url_spam_classification.csv。
URL - Spam or Not Spam - Classification Dataset
This dataset contains about 87.5K URLs in which one - third are flagged as a spam URL and restrict are not spam. It can be used to create a binary classification model.
Credits:
The dataset was created by The Pudding. This dataset of every link is found in different newsletters. The flagging system identifies if a link is a spam or not, as it parses links from over 100 newsletters every 30 minutes. A link is programatically f flagged if it appears 3+ times in a single newsletter or contains a likely subscribe/unsubscribe URL.
If you use this dataset, don't forget to cite the author.