Regardless of the "big data" concept is not a trap, our era, the internet giant sitting on a huge amount of information is no denying the fact that the basis for the survival of Community products and social products is the data from the user.
How do they eight, recount make you feel the big data? For example, at the end of last year, you must have seen many friends sharing a "custom" picture in the micro-trust circle, in the micro-credit product growth process of the timeline to mark the time you join; You may be logged in to the watercress, only to find through a special memory channel, Watercress has helped you record a year's music footprint, from which day to register one day to listen to the first song that day is very sad ... There is no omission; If you are aware of the user, you must have taken a "time machine", until this time a group of data to let you suddenly find that you have written the answer has been shared by tens of thousands of people ...
these intimate and very sensational products behind the product, is based on the most basic form of data mining. These thoughtful data products, often for you to worry about writing the annual summary while worried about the end of the year red envelopes shrink the gloomy life to provide some consolation (except Alipay's bill, this is almost a reminder of the past year has made too many sins) threatening letter it ... )
do you know how SNS hegemony Facebook is playing with big data? Facebook knows when you're dating someone and when to break up-yes, that's easy.
, a recent article in The Atlantic, published an interesting diagram (below) showing the number of Facebook users posting over time. What does that mean?
This picture is from Facebook. Just on the third day of this year, Facebook, through its development blog, unveiled a discovery by its research team, the data researcher, that using the Facebook statistics, you can tell whether or when the person who posted the spark of love. Lenovo has an ancient poem "Don't Know the truth, only in this mountain", in other words, Facebook may be a step ahead of some couples to detect the love between them.
Like the traditional line of lovers, social networking users can also experience the so-called courtship phase. Carlos Diouk, a Facebook scientist, Carlosdiuk that two Facebook users will post more postings along the timeline, in a courtship period. And once you really look at each other is the right person, two people in each other's Facebook message board post will be reduced. The reason may be that lovers who are in love spend more time together.
Diouk this with numbers to explain everything:
we found through a lot of data that in the 100 days before becoming a lover, the two people who fell in love in the future slowly increased each other's postings. Assuming that the day of the relationship officially begins with the "0th Day", the number of such posts is getting smaller from the "0th Day". We found that the "0th Day" before the highest post peak of 12 days, the average daily hair 1.67 stickers, and "0th days" after posting at least 85 days, the average daily release of 1.53 stickers.
with a bit of common sense and psychological analysis, explain this phenomenon is simpler: after courtship between lovers, both sides increased time, online interaction gives the offline real world interaction.
Diouk said the data also showed another interesting trend, namely, after the farewell to single, The love Between lovers rose, interactive content will be more and more sweet, transfer positive energy. As Facebook's chart below shows, on the first day after the 0th and 0th days, there was a sharp increase in the number of posts between lovers (pictured above).
Facebook, which has reached 270 million of its active users, has mastered hundreds of millions of such user information, . The data collected by the Facebook analysis were for couples who announced their love anniversary between April 2010 and October 2013, and did not include users who changed their relationships. In the analysis of Lovers love each other, mainly for English users.
Diouk's colleague, another scientist at the Facebook data research team, Goden Start (bogdanstate) also revealed two interesting findings:
first, if a relationship that grows through Facebook lasts more than three months, it's likely to last for four years or more;
second, the most likely month for lovers to break up is May, June and July.
This is clearly the pace of the job of the people who are going to replace psychologists and social research.
But you might say that this kind of research is pretty much a Valentine's Day marketing, right? To be honest with you, Facebook really likes to use Valentine's Day time to play around with data analysis.
as early as 2012, Facebook's data research team began making interesting attempts to use users ' active public sentiment data. At the end of 2011, Facebook began to allow users to share their listening habits (data from the Spotify plug-in) on social networks, and Facebook's data-work teams started working at the same time.
These new data engineers, with a gossip, combine the two concepts of emotion and music to discover which songs they like to play when they start a new relationship, and which songs are often mentioned after they break up. We don't know the specific analysis tools, but look at the list posted on Valentine's Day in 2012, is it more flattering and more fun than just a Valentine's Day promotional ad?
new feelings began when people's favorite songs: Don ' twannagohome (musicians Jasonderulo "Don't want to Go Home"), and the most popular song of lovelorn songs TOP10 include:
Accordingly, when people break up at the top of the song is Thecave (Danielekfavemumford&sons's "cave"), and the love of the favorite track TOP10 include:
Thecave "Bymumfordandsons
"Crewlove" Bydrake
"Allofthelights" Bykanyewest
"Rollinginthedeep" Byadele
"Takecare" Bydrake
"Itwillrain" Bybrunomars
"Wefoundlove" Byrihanna&calvinharris
"Callitwhatyouwant" Byfosterthepeople
"Loveyoulikealovesong" Byselenagomezandthescene
"Withoutyou" Bydavidguettafeaturingusher
Aside from the fact that you smiled, Facebook made the results available on a data-based recommendation engine. Product engineers have launched new social services based on a variety of speculative results-giving users the most consistent track.
Facebook's data mining team is like a group of magicians who have mastered the "mind-reading" of Love, and Ren (Chang) Love (Qing) starts using big data, which looks more grounded. This makes people think of the domestic big and small marriage platform and community, is not yet aware of their stay in the 1.0 era? In the future, true matchmaker and "bosom sister" may be social networking sites!
The content source of this page is from Internet, which doesn't represent Alibaba Cloud's opinion;
products and services mentioned on that page don't have any relationship with Alibaba Cloud. If the
content of the page makes you feel confusing, please write us an email, we will handle the problem
within 5 days after receiving your email.
If you find any instances of plagiarism from the community, please send an email to:
info-contact@alibabacloud.com
and provide relevant evidence. A staff member will contact you within 5 working days.