BN-AuthProf
收藏资源简介:
BN-AuthProf数据集是由普雷米尔大学的研究人员创建的,专门用于孟加拉语作者在社交媒体上的文本分析。该数据集包含30,131条来自300位匿名作者的社交媒体帖子,标签包括作者的年龄和性别。数据集的创建过程包括手动收集和标注,确保了数据的质量和隐私保护。该数据集主要用于机器学习模型的性别和年龄分类任务,旨在解决社交媒体文本分析中的作者特征提取问题,具有广泛的应用前景,包括市场营销、安全、法医语言学、教育和刑事调查等领域。
The BN-AuthProf dataset was developed by researchers at Premier University, specifically tailored for Bengali author text analysis on social media platforms. It comprises 30,131 social media posts from 300 anonymous authors, with labels covering the authors' age and gender. The dataset was constructed through manual collection and annotation, which ensures its data quality and protects personal privacy. This dataset is primarily utilized for gender and age classification tasks using machine learning models, aiming to address the challenge of author feature extraction in social media text analysis. It has broad application prospects across multiple fields including marketing, security, forensic linguistics, education, and criminal investigation.




