Mashable: Twitch’s new content tags are long overdue but they’ll need back-up

Mashable: Twitch’s new content tags are long overdue but they’ll need back-up. “With a bit more than a week to go before Pride Month kicks off on June 1, Twitch is launching a new collection of 350-plus content tags aimed at boosting the discoverability of marginalized voices. It’s a ridiculously late change for a tagging feature that was first introduced in 2018, but still a welcome one for content creators on the site who have long sought ways to increase their visibility on a crowded and noisy streaming platform.”

ScienceDaily: Boosting the popularity of social media posts

ScienceDaily: Boosting the popularity of social media posts. “Computer scientists created a new algorithm to recommend tags for social media posts which should boost the popularity of the post in question. This algorithm takes into account more kinds of information than previous algorithms with a similar goal. The result is a measurably improved view count for posts which use the tags recommended by this new algorithm.”

Kris Shaffer: Mining Twitter data with R, TidyText, and TAGS

Kris Shaffer: Mining Twitter data with R, TidyText, and TAGS. “One of the best places to get your feet wet with text mining is Twitter data. Though not as open as it used to be for developers, the Twitter API makes it incredibly easy to download large swaths of text from its public users, accompanied by substantial metadata. A treasure trove for data miners that is relatively easy to parse. It’s also a great source of data for those studying the distribution of (mis)information via digital media.”

Digital Archive of Children’s Books Subject of Tagging Project

The ABC Books Digital Archive at Princeton was the subject of a large and fascinating tagging project. “ABC Books is a digital archive of over fifty rare and historical children’s alphabet books, available to view page-by-page. The project is primarily pedagogical in nature. Linked to the English Department’s ‘Children’s Literature’ course, it provides an opportunity for enrolled undergraduates to complete digital humanities work for course credit as well as introduces graduate student AIs to teaching and assessing digital humanities work…. During the spring semester 2016, we asked our students to help us develop a comprehensive search function for the site. For the first step, each enrolled student added at least one hundred ‘tags’ to the archive. With well over two hundred students taking the course, we ended up with a staggering 50,000+ tags.”