Skip to content

What G+ thinks you like to read…

The latest incarnation of “What’s hot”…

Google plus always has had a content discovery feature. In the past that have been the infamous “What’s hot…” entries. Postings that went into that category usually attracted a ton of spammers and even more haters, and one had a pretty blood crusted banhammer until the waves were through. Ask me how I know…

The current incarnation of “What’s hot” is marginally better at selecting and offering content, because it is somewhat more personalised. This is actually interesting, because the top bar shows a list of clickable keywords, which can give you a way to filter and also show you what Google plus would associate with your behavior.

My list is: (+ = correct) (- = incorrect) (f = probably suggested because of the people I follow, not an actual interest) (o = neutral) (i = only ironically)

“Machine Learning” (+), “Architecture” (+), “Electric Cars” (+), “Interactive Maps” (+), “Astronomy” (+), “European Union” (+), “Retrocomputing” (o), “Star Trek” (+), “Tabletop RPGs” (+), “Articles to get you thinking” (o), “North American National Parks” (o), “Artificial Intelligence & Robotics” (+), “All Things Google” (+), “Ingress” (-, f), “Bikes & Cycling” (+) , “Computer Security” (+), “Fashion” (+), “Vinyl” (-), “Audio” (-), “Project Management” (o), “Steampunks” (+), “Tennis” (-), “Mighty Morphin Power Rangers” (-), “Gardening” (i), “Marine Life” (+), “Chemistry” (+), “Comics” (o), “Medical Science” (+), “Electronics” (+), “Magic: The Gathering” (-), “Lighting” (+), “Destination: Toronto” (f), “Fungi” (f), “Scuba Diving” (f), “Knitting & Crochet” (f), “Norse Mythology” (f), “Potterheads” (f), “Pest Control” (-), “Nature Photography” (o), “K-Pop” (f), “Dollhouse Miniatures” (-), “Amazing Earth” (o), “Maps & Globes” (o), “Chess” (-), “Landscaping” (i), “Toy Models & Crafts” (o), “The Global Economy” (+), “Woodworking” (f), “Coffee & Tea” (o), “Weddings” (o), “Cats and Dogs” (-)

Google+ Passion Cloud for me

Assuming that this is being generated by producing a set of interlocking classifiers and machine learning instead of simply aggregating over my list of followed people, this is at the same time pretty accurate and a big fail. There are huge gaps and lost opportunities for generalisation: All that Science can be subsumed under a larger umbrella of “Current Science”, the fashion and steampunk things fail to cover Victoriana and Gründerzeit, Cosplay is missing completely, the landscape gardening is only ironically (when computer science fails, again, and falls on it’s face), and general computer science as well as many specific CS topics fail to show up at all. Also, the (-) in the list are borderline WTF.

This tells us something about the value and limits of machine learning classifiers applied to human personalities.

Published inComputer ScienceScience

Be First to Comment

Leave a Reply

Your email address will not be published. Required fields are marked *