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 1808.03027cs.CLcs.IR
收藏

新闻文章的情感内容分析与知识提取

Sentimental Content Analysis and Knowledge Extraction from News Articles

Ferdowsi University of Mashhad(马什哈德菲尔多西大学)

Mohammad Kamel, Neda Keyvani, Hadi Sadoghi Yazdi

摘要:

在网络时代,由于技术的进步,人类的生活发生了革命性的变化,每天都有大量的数据和信息发布在互联网上。例如,新闻机构在世界各地的网站上发布新闻。这些原始数据可能是知识提取的重要资源。这些共享数据包含情感(即,积极的、中性的或消极的);因此,情感内容提取在许多方面可以是有益的任务。提取新闻的情感说明了在一段时间内关于事件的非常有价值的信息,媒体或新闻机构对这些事件的观点。在本文中,试图提出一种方法,新闻分析,并从中提取有用的知识。首先,我们尝试提取新闻文档的噪声鲁棒情感;因此,下载与六个国家相关的新闻:美国,英国,德国,加拿大,法国和澳大利亚,5个不同的新闻类别:政治,体育,商业,娱乐和技术。本文在提取新闻文本中的情感内容的基础上,对不同国家在每5个新闻主题中的情况进行了比较。此外,我们提出了一种方法,以减少庞大的新闻数据,提取最热门的话题和新闻标题作为知识。最后,我们生成一个词模型,通过Word 2 Vec将每个词映射到一个固定大小的向量,以了解我们收集的新闻数据库中的词之间的关系。

英文摘要:

In web era, since technology has revolutionized mankind life, plenty of data and information are published on the Internet each day. For instance, news agencies publish news on their websites all over the world. These raw data could be an important resource for knowledge extraction. These shared data contain emotions (i.e., positive, neutral or negative) toward various topics; therefore, sentimental content extraction could be a beneficial task in many aspects. Extracting the sentiment of news illustrates highly valuable information about the events over a period of time, the viewpoint of a media or news agency to these events. In this paper an attempt is made to propose an approach for news analysis and extracting useful knowledge from them. Firstly, we attempt to extract a noise robust sentiment of news documents; therefore, the news associated to six countries: United State, United Kingdom, Germany, Canada, France and Australia in 5 different news categories: Politics, Sports, Business, Entertainment and Technology are downloaded. In this paper we compare the condition of different countries in each 5 news topics based on the extracted sentiments and emotional contents in news documents. Moreover, we propose an approach to reduce the bulky news data to extract the hottest topics and news titles as a knowledge. Eventually, we generate a word model to map each word to a fixed-size vector by Word2Vec in order to understand the relations between words in our collected news database.

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。

↑