arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2201.00690cs.IRcs.LG
收藏

通过社区池改进Twitter中的主题建模

Improved Topic modeling in Twitter through Community Pooling

Instituto en Ciencias de la Computación, CONICET - Universidad de Buenos Aires(布宜诺斯艾利斯大学计算机科学研究所,CONICET);Departamento de Computación, Universidad de Buenos Aires(布宜诺斯艾利斯大学计算机系)

Federico Albanese, Esteban Feuerstein

摘要:

社交网络在信息和新闻的传播中发挥着重要作用。描述消息内容对于不同的任务变得至关重要,例如突发新闻检测,个性化消息推荐,虚假用户检测,信息流描述等。然而,Twitter帖子很短,并且通常不如其他文本文档连贯,这使得有效地将文本挖掘算法应用于这些数据集具有挑战性。Tweet-pooling(将tweets聚合成较长的文档)已被证明可以提高自动主题分解,但此任务中实现的性能取决于池方法。在本文中,我们提出了一个新的池方案的主题建模在Twitter上,组推文的作者属于同一个社区(一组用户谁主要是相互作用,但不与其他群体)的用户交互图。我们提出了一个完整的评估这种方法,国家的最先进的计划和以前的池模型的聚类质量,文件检索任务的性能和监督机器学习分类得分。结果表明,我们的社区投票方法优于其他方法的大多数指标在两个异构数据集,同时也减少了运行时间。这在处理大量嘈杂和简短的用户生成的社交媒体文本时很有用。总的来说,我们的研究结果有助于改进识别Twitter数据集中潜在主题的方法,而不需要修改主题分解模型的基本机制。

英文摘要:

Social networks play a fundamental role in propagation of information and news. Characterizing the content of the messages becomes vital for different tasks, like breaking news detection, personalized message recommendation, fake users detection, information flow characterization and others. However, Twitter posts are short and often less coherent than other text documents, which makes it challenging to apply text mining algorithms to these datasets efficiently. Tweet-pooling (aggregating tweets into longer documents) has been shown to improve automatic topic decomposition, but the performance achieved in this task varies depending on the pooling method. In this paper, we propose a new pooling scheme for topic modeling in Twitter, which groups tweets whose authors belong to the same community (group of users who mainly interact with each other but not with other groups) on a user interaction graph. We present a complete evaluation of this methodology, state of the art schemes and previous pooling models in terms of the cluster quality, document retrieval tasks performance and supervised machine learning classification score. Results show that our Community polling method outperformed other methods on the majority of metrics in two heterogeneous datasets, while also reducing the running time. This is useful when dealing with big amounts of noisy and short user-generated social media texts. Overall, our findings contribute to an improved methodology for identifying the latent topics in a Twitter dataset, without the need of modifying the basic machinery of a topic decomposition model.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑