The story appears on

Page A12

January 17, 2015

GET this page in PDF

Free for subscribers

View shopping cart

Related News

Home » Feature » News Feature

Study provides accurate readings that can be used

Q: Why do you use Facebook “likes” as your major source for the computer analysis?

A: Facebook likes are one generic kind of digital footprint. In other words, they provide similar information as other digital footprints.

For instance, liking a brand or a product is similar to obtaining online order history; music-related likes provide similar information as a personal music library; liked websites allow for approximating web browsing behavior.

Consequently, our findings can be generalized to other digital footprints such as web-browsing logs, web search queries, or purchase records.

Q: The study uses self-rating as the criteria. How good is that as criteria of personality?

A: We compared how well the self-ratings align with computers' predictions versus judgments provided by others they know in real life (eg, friends, family, spouse etc). The results show that computer models better align with self-ratings than other human beings.

It's possible that for some personality traits, other people might know us better than we know ourselves. To further confirm our results, we indeed used other criteria in the study to assess accuracy, as well.

For example, we looked at the external validity, measuring how well a judgment aligns with the actual behavior of the person in real life. It turns out that computer predictions are more accurate than ratings provided by people's friends/family in all areas but one, and in some cases, computer predictions are even better than self-ratings.

Q: How can your study be applied in real life?

A: Predicting personality traits could be used in a number of practical settings.

In marketing, advertisers could improve product recommendation and tailor their marketing message based on personality (eg, a bungee jumping company might want to target people who are extroverted).

In recruitment and career planning, people could be matched with jobs and careers using personality (eg, matching well-organized people with accounting). In online dating, personality could be used so people with similar personality can be easily paired.

People may choose to augment their own intuitions and judgments with the kind of data analysis when making important life decisions such as choosing activities, career paths, or even romantic partners. Such data-driven decisions may well improve people’s lives.

Q: How about the privacy issue?

A: Predicting personality, like any other technology is morally neutral.

Certainly, we need to proceed with caution as today’s technology scales well and thus can benefit/harm large numbers of people.

Thus, we should design the policies and technology in a way that minimizes associated risks. Two principles should guide us: transparency and control.

First, we need to help users understand which of their personal data is out there, how it is being used and how it might be used. Second, we need to enable users to take full control of their data and decide for which purpose it is to be used.




 

Copyright © 1999- Shanghai Daily. All rights reserved.Preferably viewed with Internet Explorer 8 or newer browsers.

沪公网安备 31010602000204号

Email this to your friend