Population Statistic: Read. React. Repeat.
Monday, August 04, 2021

Anyone who resents reading through Yahoo! Shortcuts and similar automated-tagging links in Web content should get a chuckle out of a recently-publicized snafu resulting from said keywording:

The phrase “underage girls,” now added to a list of thousands of previously blocked terms, will never again generate a Yahoo Shortcut, the company said. But the incident highlights how difficult it can be for publishers to keep a tight rein on their sites in this age of user-generated content.

Internet publishers are increasingly relying on automated systems to tag phrases of interest and, in some cases, to provide links to other sites. With legions of YouTube users, Flickr photographers and anonymous bloggers posting floods of their own, largely unsupervised material, it’s impossible for publishers using automation to exercise total control.

“No matter how sophisticated you make these automated systems, you’re not going to make them perfect, and all you can really strive for is to tune them as you go along,” said Lauren Weinstein, co-founder of People for Internet Responsibility. Still, he said, in this case “it’s pretty clear there was a lapse in terms of the quality control of Yahoo’s keyword list.”

Actually, I don’t think a mis-tag has to be salacious, or even controversial, to be obtrusive. To say that the algorithms aren’t perfect is a laughable understatement — because they’re based on keywords, they’re downright primitive. Context is often lost, and you wind up with unconventional word pairings and other phraseology that gets inappropriately assigned an irrelevant link.

The clearest examples I can think of are from sports news. I can’t tell you how many sports articles I come across where, for instance, the word “stars” gets auto-tagged with a link relating to the NHL’s Dallas Stars — even though the usage has nothing to do with that specific team. The same thing happens with any number of team names and other terms that are so simple that they, paradoxically, turn out tricky for the tagging program.

I realize this auto-linking represents value-added revenue potential, and it’s hard for publishers to give up that money. But really, it just looks sloppy, and the “value” added comes off as crass. Either have a human vet those links before making them live — probably too costly as a realistic option — or else ditch them altogether. The readership certainly isn’t going to miss them.

by Costa Tsiokos, Mon 08/04/2021 08:03:59 AM
Category: Internet, Media
| Permalink | Trackback |

Feedback »
Leave a comment


PLEASE NOTE: Various types of comment moderation may be triggered once you hit the "Say It!" button below. Common causes for this are the inclusion of several hyperlinks and/or spam words in the comment field. Please do not hit the "Say It!" button more than once. If you feel your comment is being blocked without cause, feel free to email me about it.