Rana el Kaliouby: This app knows how you feel -- from the look on your face
رانا ئەل کالیۆبی: ئەم ئەپە دەزانێت هەست چۆنە -- بە دەربڕینی دەم و چاوتا
What if a computer could recognize your facial expression, and react to how you feel? Rana el Kaliouby sees big possibilities in making technology emotionally aware. Full bio
Double-click the English transcript below to play the video.
every aspect of our lives,
ههموو بوارهكانی ژیانمان ههیه،
to how we do business and make decisions,
تا چۆنیهتی بازرگانیكردن و بڕیاردانیشمان،
how we connect with one another.
چۆنیەتی مامەڵەكردنمان لەگەڵ یەكتری
in a world like this,
more and more of our lives like this --
بەم شێوەیە دەژین
from my daughter last night --
back into our digital experiences.
ئەزموونە دیجیتاڵییەكانمان
a Ph.D. program at Cambridge University.
لە زانكۆی كامبریدج
who had to stay in Egypt,
دەبوایە لهمیسر بمێنێتەوە
away from home,
لە ووڵاتی خۆمەوە دوورە
more hours with my laptop
بەسەردەبەم لەسەر لاپتۆپ
مرۆڤێكی تر بەسەری دەبەم
had absolutely no idea how I was feeling.
قهت هەستی نەدەكرد ئاخۆ من هەستم چۆنە
سترێسم هەبێت، سەرم لێشێوابێت و
online with my family back home,
لەگەڵ ماڵەوە دەكرد بە ئینتەرنێت
disappeared in cyberspace.
وندەبن لەناو تۆری ئینتەرنێت
and on some days I was actually crying,
رۆژیش دەستمدەكرد بەگریان
these emotions was this.
ئهم ههستانهم دهگهیاند ئهم شته بوو.
has lots of I.Q., but no E.Q.;
زۆری ههیه بهڵام بهبێ سۆز؛
but no emotional intelligence.
بهڵام بێ زیرهكی سۆزی.
could sense our emotions?
به سۆزهكانمان بكات؟
how we felt and reacted accordingly,
چۆنه و كاردانهوهیان بهوپێیه بێت.
intelligent friend would?
هۆشمهندی سۆزدارمان دهیكات؟
and respond to our emotions,
ههستمان بخوێنێتهوه و وهڵامی بۆ ههبێت،
به روخساری مرۆڤ بوو.
one of the most powerful channels
social and emotional states,
گهیاندنی هەست و سۆزمان.
facial muscle movement an action unit.
ماسولكهیهكی رووخسار یهكهیهكی كاره.
which is the main component of a smile.
كه پێكهێنهری سهرهكی بزهكردنه.
some smiles going on.
باههندێ زهردهخهنه بكهین.
It's the brow furrow.
درزی نێوان برۆكانه.
these textures and wrinkles.
a strong indicator of a negative emotion.
نیشانهیهكی بههێزی ههستی نەرێنییە.
hundreds of emotions.
ههستی جیاواز دهردهبڕن.
these facial emotions is hard,
ئهو ههستانهی دهمووچاو زۆر قورسه،
they can be fast, they're subtle,
دهتوانن زۆر خێرابن، زۆر وردبن،
the smile and the smirk.
زهردهخهنهی فیز به نمونه وهربگرین.
but they mean very different things.
مانایان یهكجار جیاوازه.
can make you become famous.
وات لێدهكا بهناوبانگ بیت.
for a computer to be able
كۆمپیوتهر كه بتوانێ
between the two expressions.
of people we know to be smiling,
خهڵكی ناسراو.
زهردهخهنهی بەزۆریش کرد.
textures and wrinkles
پێكهاته و لۆچیهكان
لهسهر دهمووچاومان،
have common characteristics,
تایبەتمەندی هاوبهشیان ههیه،
different characteristics.
جیاوازییەکی کەمیان هەیە.
characteristics of a smile,
جیاكهرهوهی بزهكردنی ههیه.
This is a smile expression."
ئهمه زەردەخەنەیە."
how this technology works
كاركردنی تهكنهلۆژیاكه
preferably somebody with a face.
باشتره كهسێك بێت دهمووچاوی ههبێت.
from being a research project at MIT
له پرۆژهیهكی توێژینهوهوه گۆراوین
to make this technology work,
بۆ سهرخستنی تهكنهلۆژیاكه،
the core emotion engine
كرۆكی مهكینهی ههستهكه
with a camera, like this iPad.
.كامێرای ههبێت وهك ئهم ئایپاده
has essentially found Cloe's face,
دهمووچاوی كلۆی دۆزییهوه،
feature points on her face,
دهموچاوی كۆدهكاتهوه،
her mouth and her nose.
can it recognize her expression?
دهربڕینی روخساری بناسێتهوه؟
Yep, awesome. (Laughter)
ببینین. دەی زۆرباشە.
this is a genuine smile, it's great.
بزهیهكی راستهقینهیه، زۆر باشه.
go up as she smiles.
كه بزه دهكات
to see if the computer can recognize?
بزانین كۆمپیوتهرهكه دهیدۆزێتهوه؟
to make that happen.
بۆ بهدیهێنانی.
indicator of surprise.
an indicator of confusion.
نیشانهی پهشێوییه.
action units. There's many more of them.
زۆر زیاتریش ههن.
an emotion data point,
ههستهكان دهڵێین، خاڵێکی زانیاری.
to portray different emotions.
ههستی جیاواز وێنا دهكهن.
look like you're happy.
when Zayn left One Direction.
بوو کە زەین وەن دایرێکشنی بەجێهێشت
negative, so you must have been a big fan.
بۆیە ئەبێ هەوادارێکی سەرسەخت بووبێتی.
or negative an experience is,
چەندێک ئەرێنی یان نەرێنییە، و
expressive she is as well.
ئهوهیه تاچهند دهربڕه.
to this real-time emotion stream,
گهیشتایه بهو زنجیره ههستانه
with anybody she wanted to.
بیهوێت هاوبەشی بكات
12 billion of these emotion data points.
داتا پۆینتی ههستانهمان كۆكردۆتهوه
database in the world.
from 2.9 million face videos,
روخسارهكان كۆكردۆتهوه،
to share their emotions with us,
لهگهڵمان شێر بكهن
as personal as our emotions,
كهسی وهك ههستهكان بكهین
ئهم پێوهره بیكهین.
that you might suspect.
رهنگه پێشبینیتان كردبێ،
their smiles last longer,
بهڵكو زیاتریش دهخایهنێ،
what it is that men and women
چ شتێكه ژنان و پیاوان
more expressive than men,
in the U.K. between men and women.
نهبینینێ لهنێوان ژنان و پیاواندا.
than younger people.
than men the same age,
بهبزهترن لهپیاوانی هاوتهمهنیان.
the most about this data
بۆمان دهربارهی ئهم داتایه
to be expressive all the time,
ههستێك دهردهبڕین،
in front of our devices alone,
لهبهردهم ئامێرهكانمان.
cat videos on Facebook.
ڤیدیۆی فهیسبووك دهكهین.
texting, shopping online,
بازاڕكردنی ئۆنلاین
مامهلهمان لهگهڵ میدیا،
and voting behavior;
خوی دهنگدان؛
or emotion-enabling technology,
یا ههستكردنی تهكنهلۆژیا.
that are especially close to my heart.
كه بهراستی لهدڵمهوه نزیكن.
can help individuals
دهبێ بۆ ئهو تاكانهی
read the faces of others,
ئهوانیتر بخوێننهوه،
on the autism spectrum interpret emotion,
دهدات ههستهكان لێكبدهنهوه،
if your learning apps
ئهپی فێربونهكهت
شێواوی و تاقهتت نهماوه،
would in a classroom.
دهیكهن لهناو پۆلدا.
مهزاجت بخوێنێتهوه،
ههستكا كه تۆ بێتاقهتی،
knows that you're stressed,
كه تۆ سترێس هەیە،
from binge eating. (Laughter)
کامبریدج بووم
emotion stream,
گواستنەوەی هەستانە، و
back home in a very natural way,
خێزانەکەم بایە لە ماڵەوە،
in the same room together?
لهههمان ژوربین پێكهوه؟
to have an emotion chip,
پارچهیهكی دهبێت بۆ ههست.
when we couldn't just frown at our device
مۆن دهكهین
you didn't like that, did you?"
ئهمهت بهدڵ نییه، وایه؟"
so many applications of this technology,
تهكنهلۆژیاكه بهكارهێنانی زۆره،
build them all ourselves,
ههموویان بكهین،
so that other developers
تا پەرەپێدەرەکانی تر
there are potential risks
مهترسی شاراوه ههیه
many years doing this,
لهمهدا سهرف كردووه،
intelligent technology
خاوهن ههست
خراپ بهكارهێنان.
part of the conversation.
بهشێك لهو گفتوگۆیه
about this technology,
لهسهر ئهم تهكنهلۆژیایه
in how it's being used.
هەبێت لە باش بەکارهێنانیا.
of our lives become digital,
بهرهو بەئەلیكترۆنیبوون دهروا،
trying to curb our usage of devices
نههێشتنی بهكارهێنانی ئامێرهكان
is to bring emotions into our technology
بگەڕێنمەوە ناو تەکنەلۆجیاکانمان و
that have separated us
we have this golden opportunity
ئهو ههله زێڕینهمان ههیه
connect with machines,
بە ئامێرەکانەوە پەیوەستین و
ABOUT THE SPEAKER
Rana el Kaliouby - Computer scientistWhat if a computer could recognize your facial expression, and react to how you feel? Rana el Kaliouby sees big possibilities in making technology emotionally aware.
Why you should listen
Rana el Kaliouby, chief science officer and co-founder of Affectiva, an MIT Media Lab spin-off, is on a mission to bring emotion intelligence to our digital experiences. She leads the company's emotion analytics team, which is responsible for developing emotion-sensing algorithms and mining the world's largest emotion data database. So far, they've collected 12 billion emotion data points from 2.9 million face videos from volunteers in 75 countries. The company’s platform is used by many Fortune Global 100 companies to measure consumer engagement, and is pioneering emotion-enabled digital apps for enterprise, entertainment, video communication and online education.
Entrepreneur magazine called el Kaliouby one of “The 7 Most Powerful Women To Watch in 2014,” and the MIT Technology Review included her in their list of the “Top 35 Innovators Under 35.”
Rana el Kaliouby | Speaker | TED.com