Real-time trending topics detection and description from Twitter content
Real-time trending topics detection and description from Twitter content
复制标题
DOI：
10.1007/s13278-015-0298-5
复制
发表时间：
2015-12-01
影响因子：
2.8
通讯作者：
Zegour, Djamel Eddine
中科院分区：
文献类型：
--
作者：
Madani, Amina;Boussaid, Omar;Zegour, Djamel Eddine
在过去的几年里，Twitter已经成为一个重要的信息来源。Twitter允许用户发送和阅读简短的基于文本的消息，称为tweets。用户们正忙碌报道他们的个人生活和周围的新闻。由于数据的异质性和巨大规模，来自不同学科的许多研究人员都对Twitter进行了研究。其中一个具有挑战性的问题是自动识别Twitter上的真实的热门话题。因此，在真实的时间中的趋势话题检测对于记者、新闻记者、分析师、电子营销专家、实时应用开发者和社交媒体研究人员理解正在发生的事情、人们之间交换的新兴趋势话题具有很高的价值。在本文中，我们提出了一种新的方法，发现许多不同的趋势主题，从鸣叫在真实的时间。我们的热门话题是针对特定的地理城镇检测的，并与Twitter上显示的热门话题进行比较。与Twitter相反，我们提出的方法区分了对应于同一趋势主题的不同术语。我们利用组成推文的关键字之间的语义相似性，通过统一使用推文词库前创建。每个热门话题都有一个描述，由十条更具代表性的推文的关键字表示。
Twitter has become, over the last years, a major source of information. Twitter enables its users to send and read short text-based messages called tweets. Users are busy reporting news about what's going around and within their personal. Numerous researchers from various disciplines have examined Twitter, due to the heterogeneity and immense scale of the data. One of the challenging problems is to automatically identify trending topics in real time on Twitter. Trending topics detection in real time is, thus, of high value to journalists, news reporters, analysts, e-marketing specialists, real-time application developers, and social media researchers to understand what is happening, what emergent trending topics are exchanged between people. In this paper, we propose a new approach that discovers many different trending topics from tweets in real time. Our trending topics are detected for a specific geographic town and compared with the top trending topics shown on Twitter. Contrary to Twitter, our proposed approach distinguishes between different terms corresponding to the same trending topic. We exploit the semantic similarity between keywords composing tweets, by unifying them using a tweets thesaurus former created. Each trending topic has a description presented by keywords of ten tweets that are more representative.