Trending topics on cable news: the newsflash package

By September 12, 2017ai, bigdata, machinelearning

(This article was first published on Revolutions, and kindly contributed to R-bloggers)

Want to know what's capturing the attention of the producers at the 24-hour cable news stations? There's no equivalent of Twitter's trending topics for the likes of CNN or BBC News, but the newsflash package for R by Bob Rudis can extract the latest trending topics from the TV news stations.

The newsflash package is an interface to the GDELT Project's Television Explorer, which provides access to the closed-captioning transcripts from seven major cable-news stations, with archives available for the past 6 years. In particular, it provides access to the top trending “entities” (in the sense of the Stanford Names Entity Recognizer), ranked by the number of sentences in which they are mentioned during the last 24 hours. You can see R code extracting the rankings here.

The newsflash package is still in alpha-test mode and only available on Github (and not yet on CRAN). Also, it seems that the GDELT API can be a little unreliable and sometimes fails to return results. Nonetheless, it looks to be a useful resource for exploring what the TV news networks are reporting.

rud.is: Teasing Out Top Daily Topics with GDELT’s Television Explorer

var vglnk = { key: ‘949efb41171ac6ec1bf7f206d57e90b8’ };

(function(d, t) {
var s = d.createElement(t); s.type = ‘text/javascript’; s.async = true;
s.src = “http://cdn.viglink.com/api/vglnk.js”;
var r = d.getElementsByTagName(t)[0]; r.parentNode.insertBefore(s, r);
}(document, ‘script’));

To leave a comment for the author, please follow the link and comment on their blog: Revolutions.

R-bloggers.com offers daily e-mail updates about R news and tutorials on topics such as: Data science, Big Data, R jobs, visualization (ggplot2, Boxplots, maps, animation), programming (RStudio, Sweave, LaTeX, SQL, Eclipse, git, hadoop, Web Scraping) statistics (regression, PCA, time series, trading) and more…




Source link