TED2010
Sebastian Wernicke: Lies, damned lies and statistics (about TEDTalks)
Laži, proklete laži i statistika (o TEDTalks)
Filmed:
Readability: 4.2
2,510,120 views
U briljantnoj ironičnoj analizi, Sebastijan Vernike upravlja statističke alate ka TEDTalks, kako bi napravio metriku za stvaranje "optimalnog TEDTalk-a" utemeljenog na ocenama korisnika. Kako ih ocenjujete? "Zaustavlja dah"? "Neuverljivo"? Ili jednostavno "Smešno"?
Sebastian Wernicke - Data scientist
After making a splash in the field of bioinformatics, Sebastian Wernicke moved on to the corporate sphere, where he motivates and manages multidimensional projects. Full bio
After making a splash in the field of bioinformatics, Sebastian Wernicke moved on to the corporate sphere, where he motivates and manages multidimensional projects. Full bio
Double-click the English transcript below to play the video.
00:16
If you go on the TED website,
0
1000
3000
Ako odete na TED sajt,
00:19
you can currently find there
1
4000
2000
naći ćete, u ovom trenutku
00:21
over a full week of TEDTalk videos,
2
6000
3000
TEDTalks snimke za celu nedelju gledanja,
00:24
over 1.3 million
3
9000
2000
preko 1,3 miliona
00:26
words of transcripts
4
11000
2000
reči u transkriptima
00:28
and millions of user ratings.
5
13000
2000
i milione ocena korisnika.
00:30
And that's a huge amount of data.
6
15000
3000
A to je ogromna količina podataka.
00:33
And it got me wondering:
7
18000
2000
Pa sam se zapitao:
00:35
If you took all this data
8
20000
2000
da uzmete sve te podatke
00:37
and put it through statistical analysis,
9
22000
2000
i statistički ih obradite,
00:39
could you reverse engineer a TEDTalk?
10
24000
2000
možete li obrnuti proces nastajanja TEDTalk-a?
00:41
Could you create
11
26000
2000
Možete li da stvorite
00:43
the ultimate TEDTalk?
12
28000
2000
vrhunski TEDTalk?
00:45
(Laughter) (Applause)
13
30000
2000
(aplauz)
00:47
And also, could you create
14
32000
2000
Isto tako, možete li stvoriti
00:49
the worst possible TEDTalk
15
34000
2000
najgori mogući TEDTalk
00:51
that they would still let you get away with?
16
36000
2000
sa kojim ćete se ipak izvući?
00:53
To find this out, I looked at three things:
17
38000
2000
Da bih ovo otkrio, posmatrao sam 3 stvari.
00:55
I looked at the topic that you should choose,
18
40000
2000
Temu koja bi trebalo da izaberete.
00:57
I looked at how you should deliver it
19
42000
3000
Kako bi to trebalo prezentovati
01:00
and the visuals onstage.
20
45000
2000
i vizuelno prikazati.
01:02
Now, with the topic: There's a whole range of topics you can choose,
21
47000
3000
Što se tiče teme - postoji čitav spektar mogućih tema,
01:05
but you should choose wisely,
22
50000
2000
ali morate birati mudro,
01:07
because your topic strongly correlates
23
52000
2000
jer je vaša tema jako povezana
01:09
with how users will react to your talk.
24
54000
3000
sa rekacijama korisnika na vaš govor.
01:12
Now, to make this more concrete,
25
57000
2000
Da konkretizujemo,
01:14
let's look at the list of top 10 words
26
59000
3000
pogledaćemo listu 10 reči
01:17
that statistically stick out
27
62000
2000
koje se statistički izdvajaju
01:19
in the most favorite TEDTalks
28
64000
2000
u omiljenim i najmanje
01:21
and in the least favorite TEDTalks.
29
66000
3000
omiljenim TEDTalk prezentacijama.
01:24
So if you came here
30
69000
2000
Dakle, ako dođete ovde da
01:26
to talk about how French coffee
31
71000
2000
govorite kako će francuska kafa
01:28
will spread happiness in our brains,
32
73000
3000
širiti sreću u našim mozgovima,
01:31
that's a go.
33
76000
2000
to će proći.
01:33
(Laughter) (Applause)
34
78000
2000
(aplauz)
01:35
Whereas, if you wanted to talk about
35
80000
2000
Sa druge strane, ako hoćete da govorite
01:37
your project involving
36
82000
2000
o svom projektu koji uključuje
01:39
oxygen, girls, aircraft --
37
84000
2000
kiseonik, devojke, letelice -
01:41
actually, I would like to hear that talk, (Laughter)
38
86000
2000
ustvari, voleo bih da čujem taj govor,
01:43
but statistics say it's not so good.
39
88000
2000
ali statistika kaže da to ne bi bilo dobro.
01:45
Oh, well.
40
90000
2000
Eh, pa.
01:47
If you generalize this,
41
92000
2000
Ako generalizujemo ovo,
01:49
the most favorite TEDTalks are those
42
94000
2000
omiljeni TEDTalk su oni
01:51
that feature topics we can connect with,
43
96000
3000
sa čijim temama se možemo povezati,
01:54
both easily and deeply,
44
99000
2000
i lako i duboko,
01:56
such as happiness, our own body,
45
101000
2000
kao što su sreća, naše telo,
01:58
food, emotions.
46
103000
2000
hrana, emocije.
02:00
And the more technical topics,
47
105000
2000
A više tehničke teme,
02:02
such as architecture, materials and, strangely enough, men,
48
107000
3000
kao arhitektura, materijali i zaista čudno, muškarci,
02:05
those are not good topics to talk about.
49
110000
3000
to nisu dobre teme za predavanje.
02:08
How should you deliver your talk?
50
113000
2000
Kako bi trebalo prezentovati vaš govor?
02:10
TED is famous for keeping
51
115000
2000
TED je poznat po tome
02:12
a very sharp eye on the clock,
52
117000
2000
što je strog po pitanju vremena,
02:14
so they're going to hate me
53
119000
2000
i zamrzeće me što ovo
02:16
for revealing this, because, actually,
54
121000
2000
otkrivam jer ustvari, trebalo bi da
02:18
you should talk as long as they will let you. (Laughter)
55
123000
2000
govorite dokle god vas puste,
02:20
Because the most favorite TEDTalks
56
125000
3000
jer su omiljeni TEDTalks
02:23
are, on average, over 50 percent longer
57
128000
2000
oni koji su prosečno 50% duži
02:25
than the least favorite ones.
58
130000
2000
od najmanje omiljenih.
02:28
And this holds true for all ranking lists on TED.com
59
133000
2000
I to važi za sve rang liste na TED.com
02:30
except if you want to have a talk
60
135000
2000
osim ako želite da držite lep,
02:32
that's beautiful, inspiring or funny.
61
137000
2000
inspirišuć ili smešan govor.
02:34
Then, you should be brief. (Laughter) But other than that,
62
139000
2000
Onda treba da ste kratki. Ali sem toga,
02:36
talk until they drag you off the stage.
63
141000
3000
pričajte dok vas ne odvuku sa bine.
02:39
(Laughter)
64
144000
2000
(smeh)
02:41
Now, while ...
65
146000
2000
E dok -
02:43
(Applause)
66
148000
6000
(aplauz)
02:49
While you're pushing the clock, there's a few rules to obey.
67
154000
3000
Dok se trkate s vremenom, poštujte par pravila.
02:52
I found these rules out by comparing the statistics
68
157000
2000
Otkrio sam ih poredeći statistiku
02:54
of four-word phrases
69
159000
2000
fraza od četiri reči
02:56
that appear more often in the most favorite TEDTalks
70
161000
3000
koje se češće pojavljuju u popularnim, nego u
02:59
as opposed to the least favorite TEDTalks.
71
164000
2000
najmanje omiljenim TEDTalks.
03:01
I'll give you three examples.
72
166000
2000
Daću vam tri primera.
03:03
First of all, I must, as a speaker,
73
168000
2000
Prvo, kao govornik, moram
03:05
provide a service to the audience and talk about what I will give you,
74
170000
3000
uslužiti publiku i pričati o onome što ću vam dati,
03:08
instead of saying what I can't have.
75
173000
2000
umesto da govorim o onome što ne mogu imati.
03:10
Secondly, it's imperative
76
175000
2000
Dugo, nikako ne smete
03:12
that you do not cite The New York Times.
77
177000
2000
da citirate "Njujork Tajms".
03:14
(Laughter)
78
179000
2000
(smeh)
03:16
And finally, it's okay for the speaker -- that's the good news --
79
181000
3000
I konačno, u redu je da govornik - to su dobre vesti -
03:19
to fake intellectual capacity.
80
184000
2000
da folira intelektualni kapacitet.
03:21
If I don't understand something, I can just say, "etc., etc."
81
186000
3000
Ako nešto ne razumem, mogu reći "i tako dalje, i tako dalje".
03:24
You'll all stay with me.
82
189000
2000
I dalje ćete me slušati.
03:26
It's perfectly fine.
83
191000
2000
To je skroz u redu.
03:28
(Applause)
84
193000
4000
(aplauz)
03:32
Now, let's go to the visuals.
85
197000
2000
Sad pređimo na vizuelno.
03:34
The most obvious visual thing on stage is the speaker.
86
199000
3000
Najvidljivija stvar na bini jeste sam govornik.
03:37
And analysis shows if you want to be
87
202000
2000
I analize pokazuju, da ako želite da budete
03:39
among the most favorite TED speakers,
88
204000
2000
među omiljenim TED govornicima,
03:41
you should let your hair grow a little bit longer than average,
89
206000
3000
treba da vam kosa bude malo duža nego prosečno,
03:44
make sure you wear your glasses and be slightly more dressed-up
90
209000
3000
pobrinite se da nosite naočare i da se doterate malo više
03:47
than the average TED speaker.
91
212000
2000
nego prosečan TED govornik.
03:49
Slides are okay, though you might consider going for props.
92
214000
3000
Slajdovi su ok, ali razmislite da koristite i rekvizite.
03:52
And now the most important thing,
93
217000
2000
I najvažnija stvar,
03:54
that is the mood onstage.
94
219000
2000
jeste raspoloženje na bini.
03:56
Color plays a very important role.
95
221000
2000
Boje igraju vrlo važnu ulogu.
03:58
Color closely correlates
96
223000
2000
Boja je blisko povezana
04:00
with the ratings that talks get on the website.
97
225000
3000
sa ocenama koje govori dobijaju na sajtu.
04:03
(Applause)
98
228000
2000
(aplauz)
04:05
For example, fascinating talks
99
230000
2000
Na primer, zapanjujući govori
04:07
contain a statistically high amount
100
232000
2000
sadrže statistički značajnu količinu
04:09
of exactly this blue color, (Laughter)
101
234000
2000
tačno ove plave boje,
04:11
much more than the average TEDTalk.
102
236000
2000
mnogo više nego prosečni govor.
04:13
Ingenious TEDTalks, much more this green color,
103
238000
2000
Ingeniozni TEDTalk, mnogo više ove zelene,
04:15
etc., et.
104
240000
2000
i tako dalje, i tako dalje.
04:17
(Laughter) (Applause)
105
242000
7000
(aplauz)
04:24
Now, personally, I think
106
249000
2000
Sad, lično, mislim
04:26
I'm not the first one who has done this analysis,
107
251000
2000
da nisam prvi koji je napravio ove analize,
04:28
but I'll leave this
108
253000
2000
ali ostaviću to
04:30
to your good judgment.
109
255000
3000
vašoj proceni.
04:33
So, now it's time to put it all together
110
258000
2000
Dakle, vreme je da sve stavimo zajedno
04:35
and design the ultimate TEDTalk.
111
260000
2000
i kreiramo vrhunski TEDTalk.
04:37
Now, since this is TEDActive,
112
262000
2000
Pošto je ovo TEDActive,
04:39
and I learned from my analysis
113
264000
2000
a iz svojih analiza sam naučio
04:41
that I should actually give you something,
114
266000
2000
da zapravo treba nešto da vam dam,
04:43
I will not impose the ultimate
115
268000
2000
neću vam nametnuti najbolji
04:45
or worst TEDTalk on you,
116
270000
2000
ili najgori TEDTalk,
04:47
but rather give you a tool to create your own.
117
272000
2000
već pre alat da sami stvorite svoj.
04:49
And I call this tool the TEDPad.
118
274000
3000
Taj alat zovem TEDPad.
04:52
(Laughter)
119
277000
3000
(smeh)
04:55
And the TEDPad is a matrix
120
280000
2000
A TEDPad je matrica
04:57
of 100 specifically selected,
121
282000
2000
sa 100 posebno odabranih,
04:59
highly curated sentences
122
284000
3000
visoko organizovanih rečenica
05:02
that you can easily piece together to get your own TEDTalk.
123
287000
3000
koje možete lako sastaviti i napraviti svoj TEDTalk.
05:07
You only have to make one decision,
124
292000
2000
Morate doneti samo jednu odluku
05:09
and that is: Are you going to use the white version
125
294000
2000
a to je: Hoćete li koristiti ovu belu verziju
05:11
for very good TEDTalks,
126
296000
2000
za veoma dobar TEDTalk,
05:13
about creativity, human genius?
127
298000
2000
o kreativnosti, ljudskoj genijalnosti?
05:15
Or are you going to go with a black version,
128
300000
2000
Ili ćete koristiti crnu verziju, koja će
05:17
which will allow you to create really bad TEDTalks,
129
302000
2000
vam omogućiti da napravite vrlo loš TEDTalk,
05:19
mostly about blogs,
130
304000
2000
uglavnom o blogovima,
05:21
politics and stuff?
131
306000
2000
politici i tome slično?
05:23
So, download it and have fun with it.
132
308000
2000
Skinite ga i zabavite se sa njim.
05:25
Now I hope you enjoy the session.
133
310000
3000
Nadam se da ćete uživati u sesiji.
05:28
I hope you enjoy designing your own
134
313000
2000
Nadam se da ćete uživati stvarajući svoj
05:30
ultimate and worst possible TEDTalks.
135
315000
2000
najbolji i najgori mogući TEDTalk.
05:32
And I hope some of you will be inspired for next year
136
317000
3000
I nadam se da će neki od vas biti inspirisani da sledeće
05:35
to create this, which I really want to see.
137
320000
3000
godine naprave ovo, što stvarno želim da vidim.
05:38
Thank you very much.
138
323000
2000
Mnogo vam hvala.
05:40
(Applause) Thanks.
139
325000
10000
(aplauz)
ABOUT THE SPEAKER
Sebastian Wernicke - Data scientistAfter making a splash in the field of bioinformatics, Sebastian Wernicke moved on to the corporate sphere, where he motivates and manages multidimensional projects.
Why you should listen
Dr. Sebastian Wernicke is the Chief Data Scientist of ONE LOGIC, a data science boutique that supports organizations across industries to make sense of their vast data collections to improve operations and gain strategic advantages. Wernicke originally studied bioinformatics and previously led the strategy and growth of Seven Bridges Genomics, a Cambridge-based startup that builds platforms for genetic analysis.
Before his career in statistics began, Wernicke worked stints as both a paramedic and successful short animated filmmaker. He's also the author of the TEDPad app, an irreverent tool for creating an infinite number of "amazing and really bad" and mostly completely meaningless talks. He's the author of the statistically authoritative and yet completely ridiculous "How to Give the Perfect TEDTalk."
Sebastian Wernicke | Speaker | TED.com