地球资源数据云——数据资源详情
NLP 的网络欺凌
该数据集《cyber bullying for NLP》主要用于监督学习任务，数据形态以文本为主，应用场景偏向文本内容分析。 题目说明：It is prepared to detect cyberbullying with natural language processing. 任务类型：文本监督学习。 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：deneme.csv, newcsv.csv, tweetset.csv。 It is a data set obtained from the tweets posted on the social media platform called tweetter for the detection of cyberbullying. The github link of the team that prepared this work. You can visit for detailed information ; https://github.com/Minus100DataScience/Online - Turkce - Dogal - Dil - Isleme - Yarismasi
摘要概览
该数据集《cyber bullying for NLP》主要用于监督学习任务，数据形态以文本为主，应用场景偏向文本内容分析。 题目说明：It is prepared to detect cyberbullying with natural language processing.
任务类型：文本监督学习。
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：deneme.csv, newcsv.csv, tweetset.csv。
It is a data set obtained from the tweets posted on the social media platform called tweetter for the detection of cyberbullying.
The github link of the team that prepared this work. You can visit for detailed information ; https://github.com/Minus100DataScience/Online - Turkce - Dogal - Dil - Isleme - Yarismasi