arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2104.08396cs.DCcs.PF
收藏

使用可扩展的大数据分析Yelp数据集

Yelp Dataset Analysis using Scalable Big Data

Mohsen Alam, Benjamin Cevallos, Oscar Flores, Randall Lunetto, Kotaro Yayoshi, Jongwook Woo

摘要:

Yelp已经并将继续作为一个数据驱动的应用程序。Yelp发布了一个包含商业信息、评论、用户信息和签到信息的数据集。本文将研究此数据集,以提供描述性分析,以了解业务绩效,业务的地理空间分布,评论者的评级和其他特征,以及业务场所中签到的时间分布。通过这些分析,我们能够确定Yelp的评论、提示、精英用户和签到在过去几年里已经开始大幅下降。巧合的是,该文件还确定,加拿大人有一个更稳定的星级以及情绪评级相比,美国人。

英文摘要:

Yelp has served and will continue to serve as a data-driven application. Yelp has published a dataset containing business information, reviews, user information, and check-in information. This paper will examine this dataset to provide descriptive analytics to understand business performance, geo-spatial distribution of businesses, reviewers' rating and other characteristics, and temporal distribution of check-ins in business premises. With these analysis we are able to establish that yelp reviews, tips, elite users and check ins have started to plummet over the years. Coincidentally, the paper also establishes that Canadians have a more stable star ratings as well as sentiment ratings when compared to Americans.

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。

↑