1
00:00:10,143 --> 00:00:14,244
So some of the smallest
most insignificant work

2
00:00:14,244 --> 00:00:17,995
is everyday, cos reflect
a lot about who we are.

3
00:00:17,995 --> 00:00:20,137
And I say this not
as a linguist,

4
00:00:20,137 --> 00:00:23,506
or a computer scientist
but as a social psychologist.

5
00:00:23,506 --> 00:00:25,743
And today I'd like
to tell you a story

6
00:00:25,743 --> 00:00:28,345
that summarizes
a lot of the research

7
00:00:28,345 --> 00:00:31,060
that my colleagues,
my students and I have done,

8
00:00:31,060 --> 00:00:34,623
that have helped me
to come to this realization.

9
00:00:34,623 --> 00:00:38,137
Now several years ago I was studying
the nature of traumatic experience

10
00:00:38,137 --> 00:00:40,607
and how it is related
to physical health

11
00:00:40,607 --> 00:00:44,927
and kept finding
that just completely perplexed me.

12
00:00:44,927 --> 00:00:48,965
Basically when people have
a major traumatic experience in their life,

13
00:00:48,965 --> 00:00:52,355
they are much more likely
to get sick after that event,

14
00:00:52,355 --> 00:00:54,462
if they keep the events secret,

15
00:00:54,468 --> 00:01:02,145
than if they actually
talk to other people.

16
00:01:02,145 --> 00:01:07,127
So, this really bugged me.
So keeping a secret it seems

17
00:01:07,127 --> 00:01:09,319
is somehow toxic.

18
00:01:09,319 --> 00:01:12,320
So this led me
to run some experiments

19
00:01:12,320 --> 00:01:14,442
where we brought people
in the laboratory

20
00:01:14,442 --> 00:01:16,863
and we asked them to write about

21
00:01:16,863 --> 00:01:21,175
the most traumatic experiences they've had,
especially if they'd kept them secret.

22
00:01:21,175 --> 00:01:23,632
And these were big traumas,
these were things like rape.

23
00:01:23,632 --> 00:01:27,808
They were like major public humiliations
or failure.

24
00:01:27,808 --> 00:01:31,285
And the results that we got
from this this study were stunning.

25
00:01:31,285 --> 00:01:35,725
We discovered that having people write
as little as fifteen minutes a day,

26
00:01:35,725 --> 00:01:37,740
for 3 or 4 consecutive days,

27
00:01:37,740 --> 00:01:41,479
brought about meaningful changes
in people's physical health

28
00:01:41,479 --> 00:01:44,015
and even their immune function.

29
00:01:44,015 --> 00:01:51,006
Translating up, saying experiences
into words makes a difference, but why?

30
00:01:51,006 --> 00:01:54,777
Since then there have been hundreds
of studies done by labs all over the world

31
00:01:54,777 --> 00:01:59,764
trying to answer this and they haven't
come up with a single explanation.

32
00:01:59,764 --> 00:02:04,746
My own approach was to actually look
at the essays that these people wrote,

33
00:02:04,746 --> 00:02:06,735
and try to figure out,

34
00:02:06,735 --> 00:02:08,856
was there something about the essays
that could predict

35
00:02:08,856 --> 00:02:11,565
who would benefit
from writing versus who wouldn't?

36
00:02:11,565 --> 00:02:14,013
I tried and I couldn't figure it out.

37
00:02:14,013 --> 00:02:16,745
So I got a number of psychologists
and other experts

38
00:02:16,745 --> 00:02:19,689
to read and write hundreds of these essays,

39
00:02:19,689 --> 00:02:22,974
and they couldn't see a pattern either;

40
00:02:22,974 --> 00:02:25,053
I needed to try some other strategies.

41
00:02:25,053 --> 00:02:27,871
So, with the help of
one of my graduate students,

42
00:02:27,871 --> 00:02:30,228
Martha Francis,
we wrote a computer program.

43
00:02:30,228 --> 00:02:33,900
And the idea of this computer program
was to go into any given text

44
00:02:33,900 --> 00:02:36,380
and calculate the percentage
of words in their texts

45
00:02:36,380 --> 00:02:39,866
that were positive emotion words,
negative emotion words

46
00:02:39,866 --> 00:02:46,914
or words related to topics such as death
or sex or violence or religion or family.

47
00:02:46,914 --> 00:02:49,190
And as long as we were writing
the computer program,

48
00:02:49,190 --> 00:02:51,976
I thought well let's go ahead and
throw in some parts of speech,

49
00:02:51,976 --> 00:02:56,715
pronouns, prepositions.
Why? Because it was easy, who cares?

50
00:02:56,715 --> 00:03:01,413
So, I go back, start to analyze
these traumatic essays,

51
00:03:01,413 --> 00:03:06,013
and quickly discover that the content
of what people were writing about

52
00:03:06,013 --> 00:03:09,243
didn't matter in terms of
if they improved in their health or not,

53
00:03:09,243 --> 00:03:15,385
instead, it was these junk words, pronouns,
articles, prepositions and so forth

54
00:03:15,385 --> 00:03:19,347
that did matter.
Now think about this.

55
00:03:19,347 --> 00:03:23,120
Here people are writing about
deeply disturbing issues

56
00:03:23,120 --> 00:03:29,034
and the actual topics that dealt with
tragedies, devastation, horrible things,

57
00:03:29,034 --> 00:03:31,512
the topics themselves
and the words associated

58
00:03:31,512 --> 00:03:33,890
with those topics made no difference.

59
00:03:33,890 --> 00:03:38,622
Instead these little words
like "I" and "the" and "and" did matter.

60
00:03:38,622 --> 00:03:41,889
I'd been looking for the obvious,
but in fact

61
00:03:41,889 --> 00:03:44,758
I'd been paying attention
to what people were saying,

62
00:03:44,758 --> 00:03:47,637
but not how they were saying it.

63
00:03:47,637 --> 00:03:51,883
So how do I go about
analyzing what verus how?

64
00:03:51,883 --> 00:03:54,426
Well, it turns out that they're
different kinds of classes of words

65
00:03:54,426 --> 00:03:57,757
that look at this distinction,
and one of them is

66
00:03:57,757 --> 00:03:59,531
if you're looking at
what people are writing about,

67
00:03:59,531 --> 00:04:04,786
you look at what are called content words.
These are nouns and regular verbs

68
00:04:04,786 --> 00:04:08,231
and adjectives and some adverbs.
These are the stuff of thought,

69
00:04:08,231 --> 00:04:11,979
these were the stuff of communication.
We were trying to talk to somebody.

70
00:04:11,979 --> 00:04:16,543
Google and search terms
are all based on these content words.

71
00:04:16,543 --> 00:04:19,165
The other group of words
are a class of words

72
00:04:19,165 --> 00:04:21,526
that are generally called
function words.

73
00:04:21,526 --> 00:04:27,084
And function words are made up
of the most boring words you can imagine.

74
00:04:27,084 --> 00:04:31,141
They're made up of pronouns:
"I", "me", "he", "she";

75
00:04:31,141 --> 00:04:37,560
prepositions: "to", "of", "for";
auxillary verbs: "am", "is", "have" â

76
00:04:37,560 --> 00:04:42,128
I'll have to wake you up if I keep talking
about these function words.

77
00:04:42,128 --> 00:04:46,758
But it turns out these
function words are really interesting,

78
00:04:46,758 --> 00:04:52,461
because, first of all, there's only about
five hundred function words in English,

79
00:04:52,461 --> 00:04:57,369
so they account for far less than 1%
of all the words we know, we hear, we read.

80
00:04:57,369 --> 00:05:03,893
Nevertheless, they reflect 55% to 60% of
all the words that we are surrounded with,

81
00:05:03,893 --> 00:05:06,784
they're everywhere,
but we don't pay attention to them.

82
00:05:06,784 --> 00:05:10,142
In English and in other languages,
they're the shortest words there are,

83
00:05:10,142 --> 00:05:12,710
and when they're spoken
or when you're reading,

84
00:05:12,710 --> 00:05:16,583
they zip into your brain
at the speed of less than 0.2 seconds,

85
00:05:16,583 --> 00:05:20,538
meaning that they're processed
essentially non-consciously.

86
00:05:20,538 --> 00:05:22,933
But there's something
even more interesting about them,

87
00:05:22,933 --> 00:05:26,897
they are social,
they are profoundly social.

88
00:05:26,897 --> 00:05:29,399
Let me give me an example,
let's say you're walking along,

89
00:05:29,399 --> 00:05:32,396
you see a note on the ground,
you pick it up and it says,

90
00:05:32,396 --> 00:05:35,583
"I am placing it on the table."

91
00:05:35,583 --> 00:05:37,732
Well, that kinda makes sense,
kinda doesn't.

92
00:05:37,732 --> 00:05:41,788
"I'm placing it on the table" â there's
2 content words, "placing" and "table";

93
00:05:41,788 --> 00:05:43,865
all the rest are function words:

94
00:05:43,865 --> 00:05:47,955
"I", "am", "it", "on", "the".

95
00:05:47,955 --> 00:05:51,328
Now the reason this doesn't
make sense to most of us is

96
00:05:51,328 --> 00:05:53,444
who was "I"?
No idea.

97
00:05:53,444 --> 00:05:56,687
"Am" implies present tense.
When was it written?

98
00:05:56,692 --> 00:05:59,221
"It"? Pfft, no idea what "it" is.

99
00:05:59,221 --> 00:06:02,733
"On the table", "the table"
means it's a table

100
00:06:02,733 --> 00:06:04,832
that the author knew about

101
00:06:04,838 --> 00:06:07,704
and the intended recipient
of this note knew about,

102
00:06:07,704 --> 00:06:14,025
but nobody else did. And, in fact,
this note only has meaning to the author

103
00:06:14,025 --> 00:06:15,833
and the recipient of the note

104
00:06:15,833 --> 00:06:18,994
at a particular time,
in a particular location.

105
00:06:19,008 --> 00:06:23,557
And, in fact, if I took that note
to this author 6 months later and say,

106
00:06:23,557 --> 00:06:27,283
"What's this all about?" there's
a good chance that the author will say,

107
00:06:27,283 --> 00:06:30,342
"No idea."

108
00:06:30,342 --> 00:06:32,960
Function words are social,

109
00:06:32,960 --> 00:06:35,984
they tell us about the author,
they tell us about the relationship

110
00:06:35,984 --> 00:06:37,783
between the author and the recipient

111
00:06:37,783 --> 00:06:41,578
and the relationship between
the author and the topic itself.

112
00:06:41,578 --> 00:06:45,731
And this is the heart of what
I want to talk to you about today.

113
00:06:45,731 --> 00:06:49,535
By analyzing function words
we start to get a sense

114
00:06:49,535 --> 00:06:51,945
of who people are,
what their relationships are,

115
00:06:51,945 --> 00:06:57,451
how they think about theirselves
and how they connect with others.

116
00:06:57,451 --> 00:06:59,343
Yeah, there're a lot of function words,

117
00:06:59,343 --> 00:07:02,959
and honestly I could talk
for several hours about function words,

118
00:07:02,959 --> 00:07:06,634
but I'm going to spare you that
and just focus on a couple today

119
00:07:06,634 --> 00:07:10,745
to just give you a flavor
of why they're so interesting.

120
00:07:10,745 --> 00:07:14,236
Let's start off with pronouns, and
let's start off with third-person pronouns

121
00:07:14,236 --> 00:07:17,337
like "he", "she", "they".

122
00:07:17,337 --> 00:07:19,332
Now it turns out some people
out there in the world

123
00:07:19,332 --> 00:07:22,543
use these third-person pronouns
at high rates

124
00:07:22,543 --> 00:07:24,947
and other people at low rates.

125
00:07:24,947 --> 00:07:27,534
What kind of person would use them?

126
00:07:27,534 --> 00:07:31,232
Well, you have to think about pronouns
and all function words

127
00:07:31,232 --> 00:07:35,784
in terms of
where are people paying attention.

128
00:07:35,784 --> 00:07:37,623
If you are using
these third-person pronouns,

129
00:07:37,623 --> 00:07:40,527
by definition you're paying attention
to other people.

130
00:07:40,527 --> 00:07:43,571
You care about other people,
you're thinking about other people,

131
00:07:43,571 --> 00:07:45,579
and people who use these at high rates

132
00:07:45,579 --> 00:07:47,709
are much more socially engaged.

133
00:07:47,709 --> 00:07:49,981
We can analyze emails,
tweets and so forth

134
00:07:49,981 --> 00:07:54,155
and get a sense of someone's
social engagement just by looking at this.

135
00:07:54,155 --> 00:07:59,335
How about first-person singular pronouns,
"I", "me" and "my"?

136
00:07:59,335 --> 00:08:01,713
OK, using the attentional arguments

137
00:08:01,713 --> 00:08:04,629
someone who's attending
to their thoughts, feelings,

138
00:08:04,629 --> 00:08:08,315
behaviors, to themselves in some way
would use these words more.

139
00:08:08,315 --> 00:08:11,615
What kind of person
do you think uses "I" words the most?

140
00:08:11,615 --> 00:08:15,674
I hope, you're sitting there,
you're thinking, "Well, somebody who's

141
00:08:15,674 --> 00:08:18,317
self-centered, self-important,
narcissistic,

142
00:08:18,317 --> 00:08:24,345
hungry for power and high in status."

143
00:08:24,345 --> 00:08:27,278
You would be completely wrong.

144
00:08:27,278 --> 00:08:33,743
In fact the person who is highest
in status uses "I" words the least.

145
00:08:33,743 --> 00:08:35,481
Let me rephrase that,

146
00:08:35,481 --> 00:08:39,376
the higher anybody is in status,
the less they use "I" words;

147
00:08:39,376 --> 00:08:44,208
the lower someone is in status,
the higher they use a "I" words.

148
00:08:44,208 --> 00:08:47,750
Now, I discovered this
by analyzing emails,

149
00:08:47,750 --> 00:08:52,543
instant messages, natural conversations,
business groups and so forth.

150
00:08:52,543 --> 00:08:57,216
And the affects were huge.
I looked at these results and I thought,

151
00:08:57,216 --> 00:09:02,624
"Wow, this must be true for other people
but it can't possibly be true for me."

152
00:09:02,624 --> 00:09:09,306
You know I love everybody equally.
So I go in and analyze my own emails.

153
00:09:09,306 --> 00:09:10,952
I'm the same as everybody else,

154
00:09:10,952 --> 00:09:15,183
I look at the email that I get
from an undergraduate student,

155
00:09:15,183 --> 00:09:18,806
"Dear Dr Pennebaker, I would like to know
if I could possibly meet with you

156
00:09:18,806 --> 00:09:20,835
because I think I need to change my grade."

157
00:09:20,835 --> 00:09:25,114
And I write back, "Dear Student,
Thank you so much for your email.

158
00:09:25,114 --> 00:09:29,730
Unfortunately, the way
the grade systems work, blah, blah, blah."

159
00:09:29,730 --> 00:09:32,225
I look at my email to the dean.

160
00:09:32,225 --> 00:09:35,074
"Dear Dean, I'm Jamie Pennebaker
and I would like to ask you

161
00:09:35,074 --> 00:09:37,370
if I could do this and if I could do that
and I could do this."

162
00:09:37,370 --> 00:09:39,715
And the dean writes back,
"Dear Jamie,

163
00:09:39,715 --> 00:09:43,959
Thank you so much for your email..."
and so forth.

164
00:09:43,959 --> 00:09:49,469
Now everybody is being completely polite,
nobody's putting anybody down.

165
00:09:49,469 --> 00:09:52,151
This is the language of power in status;

166
00:09:52,151 --> 00:09:54,526
it tells us where people
are paying attention.

167
00:09:54,543 --> 00:09:57,273
A high status person is
looking out at the world,

168
00:09:57,277 --> 00:10:00,532
the low status person tends
to be looking more inwardly.

169
00:10:00,532 --> 00:10:02,247
What about others states?

170
00:10:02,247 --> 00:10:07,237
Let's move beyond status,
let's look at emotional states.

171
00:10:07,237 --> 00:10:10,822
You would think that someone would be
paying more attention to themselves

172
00:10:10,822 --> 00:10:15,550
if they're in pain. It could be
physical pain or emotional pain.

173
00:10:15,550 --> 00:10:18,568
In fact, if we look at people
who are depressed,

174
00:10:18,568 --> 00:10:21,979
we've done many studies on this,
we know that people who are depressed

175
00:10:21,979 --> 00:10:25,739
pay attention to themselves more
and they used the word "I" more.

176
00:10:25,739 --> 00:10:28,426
In fact one of our very first studies
looked at the poetry

177
00:10:28,426 --> 00:10:31,008
of suicidal and non-suicidal poets.

178
00:10:31,008 --> 00:10:34,689
Now we did this research where
we went through, analyzed their poetry,

179
00:10:34,689 --> 00:10:37,158
and initially I thought,
where the big difference

180
00:10:37,158 --> 00:10:39,851
in the degree to which
they use negative and emotional words.

181
00:10:39,851 --> 00:10:41,852
Not true.

182
00:10:41,852 --> 00:10:47,498
Suicidal and non-suicidal poets all use
negative emotion words at high rate.

183
00:10:47,498 --> 00:10:52,109
I think it's part of the job description.

184
00:10:52,109 --> 00:10:54,904
The big difference was
their use of the word "I",

185
00:10:54,904 --> 00:10:57,946
suicidal poets use the word "I" more.

186
00:10:57,946 --> 00:11:03,213
Consider this poem, this is by Sylvia Plath
who later committed suicide.

187
00:11:03,213 --> 00:11:08,297
Listen to the way that she uses
the word "I" and first-person singular.

188
00:11:08,297 --> 00:11:14,488
I'm taking some lines from her poem
"Mad Girl's Love Song".

189
00:11:14,488 --> 00:11:17,451
I shut my eyes and
all the world drops dead;

190
00:11:17,451 --> 00:11:20,995
I lift my lid[s] and all is born again.

191
00:11:20,995 --> 00:11:23,547
(I think I made you up inside my head.)

192
00:11:23,547 --> 00:11:28,452
I fancied you'd return the way you said,
But I grow old and I forget your name.

193
00:11:28,462 --> 00:11:32,633
(I think I made you up inside my head.)

194
00:11:32,633 --> 00:11:35,643
You can almost see Plath

195
00:11:35,643 --> 00:11:39,217
embracing her sorrow,
her misery and so forth

196
00:11:39,217 --> 00:11:44,486
and you can compare her writing
with other poets, non-suicidal poets

197
00:11:44,486 --> 00:11:46,255
who write about lost love.

198
00:11:46,255 --> 00:11:50,012
When they do, you can almost see them
holding it off from a distance,

199
00:11:50,012 --> 00:11:55,189
so they're looking at it from
a more distance, third-person perspective.

200
00:11:55,189 --> 00:11:59,868
Now there's a really interesting,
important theory within psychology

201
00:11:59,868 --> 00:12:02,946
about depression.
And people who are depressed

202
00:12:02,946 --> 00:12:07,099
are thought to be people who are
very high in self-awareness or self-focus.

203
00:12:07,099 --> 00:12:12,164
And part of this is
they also tend to be extremely honest.

204
00:12:12,164 --> 00:12:19,546
In fact there are many studies showing
that they have this deficit

205
00:12:19,546 --> 00:12:23,287
and they're not able to have
positive illusions about ourselves.

206
00:12:23,287 --> 00:12:25,565
Those of us who aren't depressed
get by every day

207
00:12:25,565 --> 00:12:28,804
by holding these insane illusions
about the life.

208
00:12:28,804 --> 00:12:32,408
But these people are brutally honest.

209
00:12:32,408 --> 00:12:36,115
Now this made me wonder,
throw away depression for just a second.

210
00:12:36,115 --> 00:12:40,174
Could we turn this entire thing upside down
and find out if depressed people

211
00:12:40,174 --> 00:12:44,797
or if we could use a computer program
as a linguistic lie-detector.

212
00:12:44,797 --> 00:12:47,535
I mean for anybody.
So in fact we did some studies,

213
00:12:47,535 --> 00:12:51,112
where we brought people in the lab,
we induced them to lie or tell the truth,

214
00:12:51,112 --> 00:12:54,000
we analyze court transcripts of people
who were all found guilty,

215
00:12:54,000 --> 00:12:56,679
the half of whom were later exonerated,

216
00:12:56,679 --> 00:12:59,924
and the affects
were really quite impressive.

217
00:12:59,924 --> 00:13:01,999
We did a pretty good job at telling

218
00:13:01,999 --> 00:13:04,006
if someone who was telling
the truth versus lying,

219
00:13:04,006 --> 00:13:07,367
and one of the best words
was the use of the word "I".

220
00:13:07,367 --> 00:13:12,053
People who tell the truth use the word
"I" more, owning what they're saying.

221
00:13:12,053 --> 00:13:17,759
Liars are tending to hold off,
distancing themselves.

222
00:13:17,759 --> 00:13:23,878
Now, lie-detection and depression, status
are all some things that we can look at,

223
00:13:23,898 --> 00:13:27,538
But one of the things that I'm most
interested in now is looking at groups,

224
00:13:27,538 --> 00:13:29,640
looking at the relationship 
between two people.

225
00:13:29,640 --> 00:13:32,445
Can you tell how two people
are getting along

226
00:13:32,445 --> 00:13:36,872
by analyzing the way that they're
using function words with each other?

227
00:13:36,872 --> 00:13:40,387
And the answer is yes. We look
at the percentage of each class of words

228
00:13:40,387 --> 00:13:44,823
and we come up with the metric
that we call language style matching.

229
00:13:44,842 --> 00:13:48,244
And the more that two people are matching
in their function word use,

230
00:13:48,244 --> 00:13:50,041
the more they're on the same page,

231
00:13:50,041 --> 00:13:53,024
the more they're talking
about something in the same way.

232
00:13:53,024 --> 00:13:57,113
Now one place we started to look at this
was with speed dating.

233
00:13:57,113 --> 00:14:05,481
Now, I should tell you I love speed dating,
I would never do it in a million years,

234
00:14:05,481 --> 00:14:09,297
but I encourage all of you
to go do speed dating and when you do,

235
00:14:09,297 --> 00:14:14,832
invite a researcher along because
there is no paradigm that is better.

236
00:14:14,832 --> 00:14:17,320
We've been involved
in speed-dating projects

237
00:14:17,320 --> 00:14:21,816
where people come in and in
their four minute date, we tape-record it,

238
00:14:21,816 --> 00:14:26,794
they know we are,
and then we transcribe the way they talk.

239
00:14:26,794 --> 00:14:29,327
The more they match
in their language,

240
00:14:29,327 --> 00:14:31,379
the more likely they are
to go out on a date.

241
00:14:31,379 --> 00:14:33,242
We can predict
who will go on a date

242
00:14:33,242 --> 00:14:37,591
at rates slightly better than
the people themselves can.

243
00:14:37,591 --> 00:14:40,231
We've done studies
with young dating couples.

244
00:14:40,231 --> 00:14:46,717
To be in our study they had to give us
10 days of their instant messages or IM's.

245
00:14:46,717 --> 00:14:51,605
And then what we do is we analyze
their IM's with this style matching

246
00:14:51,605 --> 00:14:54,070
and we do much, much better
than they do

247
00:14:54,070 --> 00:14:58,122
at predicting if they'll be
together 3 months later.

248
00:14:58,122 --> 00:15:00,928
The fact is, is these words
are telling us how individuals

249
00:15:00,928 --> 00:15:03,551
and pairs of people are connecting.

250
00:15:03,551 --> 00:15:06,547
What about groups. Now this is an area
that we're now working at.

251
00:15:06,547 --> 00:15:10,303
We're looking at working groups,
some are groups that we've worked with,

252
00:15:10,303 --> 00:15:14,166
people from the business school, we look
at people in the get-to-know-you groups,

253
00:15:14,166 --> 00:15:16,746
we do educational groups.
And what we're finding is

254
00:15:16,746 --> 00:15:21,006
by looking at a group of say 5 or 6 people,
we can now get a sense

255
00:15:21,026 --> 00:15:25,512
of how productive the group will be,
and also how cohesive the group wil be,

256
00:15:25,521 --> 00:15:27,969
simply by looking at the style matching.

257
00:15:27,976 --> 00:15:30,912
Now here's where things are
beginning to get interesting:

258
00:15:30,912 --> 00:15:36,151
by tracking a group that's interacting
and say they're all interacting online,

259
00:15:36,151 --> 00:15:39,551
we can have a computer monitoring
how the group is behaving.

260
00:15:39,551 --> 00:15:46,262
Imagine for example you are in this group
and a computer coach comes to your group

261
00:15:46,262 --> 00:15:50,190
every now and then,
and a message comes and says,

262
00:15:50,190 --> 00:15:53,296
"You guys are not paying attention
to one another,

263
00:15:53,296 --> 00:15:57,396
you need to be more attentive to what
the other people are saying," or

264
00:15:57,396 --> 00:16:00,396
"You guys for the last few minutes
have strayed off topic,

265
00:16:00,396 --> 00:16:03,716
try to get back on topic,"
or that loud mouth in the group,

266
00:16:03,716 --> 00:16:07,566
the computer comes in and says,
"John, for the last 5 minutes

267
00:16:07,566 --> 00:16:11,142
you said 50% of the words,
why don't you stand back

268
00:16:11,142 --> 00:16:13,884
and courage others to talk?"

269
00:16:13,884 --> 00:16:17,199
Well, we have now created
a program that does this,

270
00:16:17,199 --> 00:16:20,602
and we've now tested it out
with hundreds of groups

271
00:16:20,602 --> 00:16:24,703
and we are getting very promising results.

272
00:16:24,703 --> 00:16:30,256
Now you can start to see why I'm so excited
about this world of function words,

273
00:16:30,256 --> 00:16:33,665
that we're now taking this
in all these directions,

274
00:16:33,665 --> 00:16:36,249
that I never would've thought about.

275
00:16:36,249 --> 00:16:39,533
We've been looking at it in terms
of looking at historical records.

276
00:16:39,533 --> 00:16:43,876
Can you tell if a particular explorer
committed suicide or was murdered?

277
00:16:43,876 --> 00:16:45,611
We've done a project on that.

278
00:16:45,611 --> 00:16:48,056
Can you look at a company and get a sense

279
00:16:48,056 --> 00:16:51,307
of how their internal communications
are working?

280
00:16:51,307 --> 00:16:55,001
How well they are connecting with the people
in their company or with their clients?

281
00:16:55,001 --> 00:16:59,752
We look at corporate earnings reports
or the quarterly phone calls

282
00:16:59,752 --> 00:17:03,112
to get a sense of the internal
group dynamics of the company.

283
00:17:03,112 --> 00:17:06,478
We've worked with the government
to try to get a sense of terroist groups

284
00:17:06,478 --> 00:17:09,813
and if they are likely to behave badly.

285
00:17:09,813 --> 00:17:14,595
We've helped people sort out
their love lives.

286
00:17:14,595 --> 00:17:19,874
You can start to see that by harnessing
the power of these function words

287
00:17:19,874 --> 00:17:26,336
We can get a sense of individuals
and groups and how people are connecting.

288
00:17:26,336 --> 00:17:32,343
Now what I would urge you to do,
I'd like you to go home tonight

289
00:17:32,343 --> 00:17:34,557
and I want you to start looking
at your emails,

290
00:17:34,557 --> 00:17:37,728
your tweets, your IM's or whatever,

291
00:17:37,728 --> 00:17:41,401
and in doing that what I hope
you start to see,

292
00:17:41,401 --> 00:17:45,182
first of all you learn a little bit more
about your relationships with others,

293
00:17:45,202 --> 00:17:49,643
but more than anything I hope
you learned a little bit about yourself.

294
00:17:49,658 --> 00:17:50,800
Thank you very much.

295
00:17:50,977 --> 00:17:56,459
(Applause)