Modality Specific Meta Features for Authorship Attribution in Web Forum Posts
Modality Specific Meta Features for Authorship Attribution in Web Forum Posts
复制标题
DOI：
--
复制
发表时间：
2011-11
期刊：
影响因子：
--
通讯作者：
T. Solorio;Sangita Pillay;Sindhu Raghavan;M. Montes-y-Gómez
中科院分区：
文献类型：
--
作者：
T. Solorio;Sangita Pillay;Sindhu Raghavan;M. Montes-y-Gómez
提出了一种新的在线论坛帖子的作者归属方法。该方法背后的思想是生成Meta特征，这些元特征捕获来自不同作者的文本之间的特定模态相似性关系。每一种情态都代表了一个特定的语言维度（句法、词汇、文体）。为了评估这种方法，我们从一个在线论坛的数据上测量预测的准确性，该论坛有多达100个候选作者。我们还将我们的结果与最先进的方法进行了比较，该方法已被证明在不同类型中表现良好。我们发现Meta功能在在线论坛领域特别有用，那里的文档非常短，这表明这是一个非常有前途的方向AA在一个现实的网络论坛场景。
This paper presents a new method for Authorship Attribution (AA) on online forum posts. The idea behind the method is to generate meta features that capture modality specific similarity relations among texts from different authors. Each modality represents a particular linguistic dimension (syntactic, lexical, stylistic). To evaluate this approach we measure prediction accuracy on data from an online forum with up to 100 candidate authors. We also compare our results with a state of the art approach that has shown to perform well across different genres. We have found the meta features to be especially helpful in the online forum domain, where the documents are very short, showing this to be a very promising direction for AA on a realistic web forum scenario.