Characterising Emergent Semantics in Twitter Lists
Characterising Emergent Semantics in Twitter Lists
复制标题
DOI：
10.1007/978-3-642-30284-8_42
复制
发表时间：
2012-05
期刊：
影响因子：
--
通讯作者：
Andres Garcia-Silva;Jeon-Hyung Kang;Kristina Lerman;Óscar Corcho
中科院分区：
文献类型：
--
作者：
Andres Garcia-Silva;Jeon-Hyung Kang;Kristina Lerman;Óscar Corcho
推特列表将推特用户组织成多个经常重叠的集合。我们认为，这些列表捕捉到了某种形式的新兴语义，这可能有助于对其进行描述。在本文中，我们描述了一种刻画列表和用户之间的语义关系的方法，通过分析列表名称中关键字的共现来推导列表和用户之间的语义关系。我们使用向量空间模型和潜在Dirichlet分配来根据共现模式来获取相似关键词。然后将这些结果与依赖WordNet的相似性度量和现有的关联数据集进行比较。结果表明，基于列表成员的关键词共现产生的同义词更多，结果与WordNet相似性度量的结果更相关。
Twitter lists organise Twitter users into multiple, often overlapping, sets. We believe that these lists capture some form of emergent semantics, which may be useful to characterise. In this paper we describe an approach for such characterisation, which consists of deriving semantic relations between lists and users by analyzing the co-occurrence of keywords in list names. We use the vector space model and Latent Dirichlet Allocation to obtain similar keywords according to co-occurrence patterns. These results are then compared to similarity measures relying on WordNet and to existing Linked Data sets. Results show that co-occurrence of keywords based on members of the lists produce more synonyms and more correlated results to that of WordNet similarity measures.