Stephen Few

We live in an era, the so-called Information Age, where data collection has become incredibly easy. The term “Big Data” gets thrown around casually as computers collect more information on us than we know how to process. Yet wise interpretation of those data is often elusive. We’re overwhelmed with it. Effective visualizations and charts can help us interpret it better, whether to present and persuade or to monitor and manage. Stephen Few, an eloquent minister-turned-data guru based in Silicon Valley, teaches us how to approach and use data from the beginning levels.

Professionally, I write software for biomedical applications that use a lot of scientific visualizations for large datasets. Although I took several nuggets of knowledge from this book (e.g., q-q plots), it was not really written for an audience like me. It’s more geared towards the wider business community, for whom data collection is a way to manage engineered systems. Rigorous biomedical scrutiny of data through careful statistics is simply not covered in this book. While for most, this tendency is surely welcomed, I honestly missed the exacting statistical theory. Still, I suspect most readers will find this book very approachable with achievable aims… even when using a common spreadsheet program.

Situated in Silicon Valley, Few clearly addresses an audience of those developing software with visualization technologies. Many times, he explicitly suggests features for new products. For software geeks like me, this trait is welcomed, but I understand that many business users, more interested in interpretation, might find it a bit off-putting. Nonetheless, I suggest it unwise to discard this whole book solely for that trait. This is the second book I’ve read by Few, and he consistently teaches me how to visualize and think about data in new ways – even as a scientist who is not deeply involved with business’s “bottom line.”

Like many books on data visualization, this work is elegantly put together with color plates communicating graphs as models. It’s simply a well-produced, pretty book. Business readers, especially decision-makers, can and should take advantage of Few’s expert wisdom. Learning a handful of pearls can easily lead to increased performance. Those involved in visualization software and the still young field of data science can likewise gain insights from Few. Again, the statistics are light, so wider audiences can access this work without intimidation. I enjoy wrestling with an active, expressive mind like Few’s and am grateful for my experiences with his writing.… (mehr)

Come contraltare a Caos quotidiano che aveva tessuto le lodi della non-strtutturazione ho preso questo libretto che ha una tesi completamente diversa: i Big Data non sono altro che l'abbindolamento che ci fa chi vende hardware e servizi di rete. Per amor di completezza, Few con i dati ci lavora; la sua tesi però - esposta in capitoli dai titoli esplicativi "Big Data, Big Whoop", "Big Data, Big Confusion", "Big Data, Big Illusion", "Big Data, Big Ruse", "Big Data, Big Distraction", "Big Data, Big Regression", è che in realtà non c'è nulla di davvero nuovo, nemmeno la grandezza relativa dei dati in questione; quello di cui abbiamo bisogno è avere persone in grado di comprendere i dati, e non credere che le macchine possano fare tutto da sole. Quello che funziona in realtà non sono i Big Data, ma per esempio il machine learning. Generalmente io sono d'accordo con Fry, anche se non arrivo alle sue posizioni talebane di un movimento Slow Data. D'altra parte, il penultimo capitolo "Big Data, Big Brother" dimostra che questi dati vengono usati eccome...… (mehr)