Local Attention Analysis and Prediction of Online News Articles in Twitter

Adjunct Proceedings of the 13th International Conference on Mobile and Ubiquitous Systems: Computing Networking and Services Pub Date : 2016-11-28 DOI:10.1145/3004010.3004042

Saki Nagaki, Yuto Yamaguchi, T. Amagasa, H. Kitagawa

{"title":"Local Attention Analysis and Prediction of Online News Articles in Twitter","authors":"Saki Nagaki, Yuto Yamaguchi, T. Amagasa, H. Kitagawa","doi":"10.1145/3004010.3004042","DOIUrl":null,"url":null,"abstract":"What is the difference between the local news and the general news? Due to a huge number of online news articles published on the Web, it has become quite important to recommend appropriate articles to users. Locality of an article is one of the important features to judge whether it gets interests from users in a specific area. In this work, we give a precise definition of local news article using the geographical distributions of the Twitter users. Using this definition, we analyze the characteristics of Japanese online news articles shared on Twitter with respect to their locality, and also propose a method for predicting the locality. Our method contributes to improving the performance of news recommendation because it becomes easy to identify the target area from local news we predict. In our experiments on Twitter and Yahoo! Japan News dataset, the results reveal that the prediction accuracy is 73%, which is 9 points higher than the naive method based on the news titles.","PeriodicalId":406787,"journal":{"name":"Adjunct Proceedings of the 13th International Conference on Mobile and Ubiquitous Systems: Computing Networking and Services","volume":"14 2 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2016-11-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"2","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Adjunct Proceedings of the 13th International Conference on Mobile and Ubiquitous Systems: Computing Networking and Services","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1145/3004010.3004042","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}

引用次数: 2

Abstract

What is the difference between the local news and the general news? Due to a huge number of online news articles published on the Web, it has become quite important to recommend appropriate articles to users. Locality of an article is one of the important features to judge whether it gets interests from users in a specific area. In this work, we give a precise definition of local news article using the geographical distributions of the Twitter users. Using this definition, we analyze the characteristics of Japanese online news articles shared on Twitter with respect to their locality, and also propose a method for predicting the locality. Our method contributes to improving the performance of news recommendation because it becomes easy to identify the target area from local news we predict. In our experiments on Twitter and Yahoo! Japan News dataset, the results reveal that the prediction accuracy is 73%, which is 9 points higher than the naive method based on the news titles.

查看原文本刊更多论文

Twitter在线新闻文章的局部关注分析与预测

本地新闻和一般新闻有什么不同?由于网络上发布了大量的在线新闻文章，向用户推荐合适的文章变得非常重要。文章的地域性是判断文章是否获得特定区域用户兴趣的重要特征之一。在这项工作中，我们使用Twitter用户的地理分布给出了本地新闻文章的精确定义。利用这一定义，我们分析了Twitter上分享的日本网络新闻文章的地方性特征，并提出了一种地方性预测方法。我们的方法有助于提高新闻推荐的性能，因为它变得容易从我们预测的本地新闻中识别目标区域。在Twitter和Yahoo!结果表明，该方法的预测准确率为73%，比基于新闻标题的朴素方法提高了9个百分点。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

求助全文

约1分钟内获得全文求助全文

来源期刊

Adjunct Proceedings of the 13th International Conference on Mobile and Ubiquitous Systems: Computing Networking and Services

自引率

0.00%

发文量