1) Researchers analyzed over 300,000 Facebook images posted by US House and Senate members to identify the race of individuals pictured and compare it to the racial demographics of their districts.
2) They found that white Democratic House members posted photos with African Americans, Hispanics, and Asians at higher rates than white Republicans.
3) Democrats' Facebook photos were more representative of the racial makeup of their districts compared to Republicans, suggesting Democrats strategically use images to signal racial identification and empathy to constituents.
Chip Ervin is a man of many accomplishments. He was born and raised in Tuscaloosa, Alabama. He became a DJ at age 14 at a local Super Skate. As a DJ, he worked with famous musicians and bands, including Evol Intent and Knick Bro Safari. Mr. Ervin started playing professional poker in 2007. Since then he has been featured as a Gulfcoastpoker.net’s top player in the South and was ranked in the top 5 of Alabama poker players.
Chip Ervin is a man of many accomplishments. He was born and raised in Tuscaloosa, Alabama. He became a DJ at age 14 at a local Super Skate. As a DJ, he worked with famous musicians and bands, including Evol Intent and Knick Bro Safari. Mr. Ervin started playing professional poker in 2007. Since then he has been featured as a Gulfcoastpoker.net’s top player in the South and was ranked in the top 5 of Alabama poker players.
Define mutation.
Develop the understanding of causes of mutation, different types of mutation, effects of mutation and prevention of mutation.
Guided by – Prof. K. M. Shamim
Is More Better?: Impact of Multiple Photos on Perception of Persona ProfilesJoni Salminen
CITE: "Salminen, J., Nielsen, L., An, J., Jung, S.G., Kwak, H., and Jansen, B. J. (2018). Is More Better?: Impact of Multiple Photos on Perception of Persona Profiles. In Proceedings of The ACM CHI Conference on Human Factors in Computing Systems (CHI2018), Montréal, Canada, 21–26 April."
Download paper: http://jonisalminen.com/wp-content/uploads/2018/08/is-more-better.pdf
Access the Automatic Persona Generation system: https://persona.qcri.org
"data: past, present, and future" day 1 lecture 2020-01-20chris wiggins
What should our future statisticians, senators, and CEOs know about the history and ethics of data? How might understanding that history provide tools and resources to future citizens navigating a future shaped by data empowered algorithms? We've developed a course that introduces students, without prerequisites, to a historical view of our present condition, in which data-empowered algorithms shape our personal, professional, and political realities. The course attempts to integrate critical data studies with functional engagement with data (in Python via Jupyter notebooks), and interleaves an applied view of ethics throughout. The intellectual arc traces from the 18th century to present day, beginning with examples of contemporary technological advances, disquieting ethical debates, and financial success powered by panoptic persuasion architectures.
The emerging field of computational social science (CSS) is devoted to the pursuit of interdisciplinary social science research from an information processing perspective, through the medium of advanced computing and information technologies.
Critical Thinking as a Skill for Democracy: A Case of Citizen Engagement with...DIPRC2019
Citizen disengagement from politics is one of the main issues in modern democracy. Technologies can be used to tap into new internal motivations for people to take part and make sense of political debate. We present a case study of citizens engaging with the replay of political election debates with a novel hypervideo technology called Democratic Replay. Results of the study show that Democratic Replay increases people’s appetite for a new type of engagement with televised elections debates which is based on the realisation of key dimensions of deliberative democracy, such as: reflecting and focusing on different aspects of the political debate, reconstructing the arguments that politicians are making, and assessing facts and evidence. The study also shows that visual analytics narratives and hypervideo navigation improve sensemaking in that they trigger questioning and changing of personal assumptions that people hold before watching the debate. This is a very encouraging result, which addresses the ongoing concern about the real value of new media in the context of political debate and democratic deliberation: specifically, the scepticism toward their capability to support people’s critical thinking rather than promote polarisation of pre-existing groups and opinions. Our research into new sensemaking technologies and hypervideo shows that new media can crucially provide new ways for citizens to detect and make sense of political manipulations, check facts versus speculations, gain new insights, and confidently inform their political choices. Results of the demographic analysis also show that Democratic Replay appealed to different demographic sub-groups with different sensemaking behaviours. This means that democratic spaces and rights cannot be interpreted uniquely and should respond to people’s personal needs, interpretation and understanding of society. Therefore, technologies for democratic public deliberation need to be designed with a variety of users in mind, and they need to be customised to the needs of different demographic groups if they aim to reach all citizens.
SDNC13 -Day2- The subjective science of persona building by Stephen Masiclat Service Design Network
The subjective science of persona building by Stephen Masiclat - Syracuse University
Personas guide design and ensure services have a relevant constituency, but they have lacked a low-cost, scientifically valid method for genesis. This presentation shows how Q-Methodolgy defines rigorous personas to guide and test the service design process
Define mutation.
Develop the understanding of causes of mutation, different types of mutation, effects of mutation and prevention of mutation.
Guided by – Prof. K. M. Shamim
Is More Better?: Impact of Multiple Photos on Perception of Persona ProfilesJoni Salminen
CITE: "Salminen, J., Nielsen, L., An, J., Jung, S.G., Kwak, H., and Jansen, B. J. (2018). Is More Better?: Impact of Multiple Photos on Perception of Persona Profiles. In Proceedings of The ACM CHI Conference on Human Factors in Computing Systems (CHI2018), Montréal, Canada, 21–26 April."
Download paper: http://jonisalminen.com/wp-content/uploads/2018/08/is-more-better.pdf
Access the Automatic Persona Generation system: https://persona.qcri.org
"data: past, present, and future" day 1 lecture 2020-01-20chris wiggins
What should our future statisticians, senators, and CEOs know about the history and ethics of data? How might understanding that history provide tools and resources to future citizens navigating a future shaped by data empowered algorithms? We've developed a course that introduces students, without prerequisites, to a historical view of our present condition, in which data-empowered algorithms shape our personal, professional, and political realities. The course attempts to integrate critical data studies with functional engagement with data (in Python via Jupyter notebooks), and interleaves an applied view of ethics throughout. The intellectual arc traces from the 18th century to present day, beginning with examples of contemporary technological advances, disquieting ethical debates, and financial success powered by panoptic persuasion architectures.
The emerging field of computational social science (CSS) is devoted to the pursuit of interdisciplinary social science research from an information processing perspective, through the medium of advanced computing and information technologies.
Critical Thinking as a Skill for Democracy: A Case of Citizen Engagement with...DIPRC2019
Citizen disengagement from politics is one of the main issues in modern democracy. Technologies can be used to tap into new internal motivations for people to take part and make sense of political debate. We present a case study of citizens engaging with the replay of political election debates with a novel hypervideo technology called Democratic Replay. Results of the study show that Democratic Replay increases people’s appetite for a new type of engagement with televised elections debates which is based on the realisation of key dimensions of deliberative democracy, such as: reflecting and focusing on different aspects of the political debate, reconstructing the arguments that politicians are making, and assessing facts and evidence. The study also shows that visual analytics narratives and hypervideo navigation improve sensemaking in that they trigger questioning and changing of personal assumptions that people hold before watching the debate. This is a very encouraging result, which addresses the ongoing concern about the real value of new media in the context of political debate and democratic deliberation: specifically, the scepticism toward their capability to support people’s critical thinking rather than promote polarisation of pre-existing groups and opinions. Our research into new sensemaking technologies and hypervideo shows that new media can crucially provide new ways for citizens to detect and make sense of political manipulations, check facts versus speculations, gain new insights, and confidently inform their political choices. Results of the demographic analysis also show that Democratic Replay appealed to different demographic sub-groups with different sensemaking behaviours. This means that democratic spaces and rights cannot be interpreted uniquely and should respond to people’s personal needs, interpretation and understanding of society. Therefore, technologies for democratic public deliberation need to be designed with a variety of users in mind, and they need to be customised to the needs of different demographic groups if they aim to reach all citizens.
SDNC13 -Day2- The subjective science of persona building by Stephen Masiclat Service Design Network
The subjective science of persona building by Stephen Masiclat - Syracuse University
Personas guide design and ensure services have a relevant constituency, but they have lacked a low-cost, scientifically valid method for genesis. This presentation shows how Q-Methodolgy defines rigorous personas to guide and test the service design process
Presenting Diverse Political Opinions: How and How Much (CHI 2010)Sean Munson
Is a polarized society inevitable, where people choose to be exposed to only political news and commentary that reinforces their existing viewpoints? We examine the relationship between the numbers of supporting and challenging items in a collection of political opinion items and readers’ satisfaction, and then evaluate whether simple presentation techniques such as highlighting agreeable items or showing them first can increase satisfaction when fewer agreeable items are present. We find individual differences: some people are diversity-seeking while others are challenge-averse. For challenge-averse readers, highlighting appears to make satisfaction with sets of mostly agreeable items more extreme, but does not increase satisfaction overall, and sorting agreeable content first appears to decrease satisfaction rather than increasing it. These findings have important implications for builders of websites that aggregate content reflecting different positions.
In the world of Big Data, there has been a lot of the research into creating efficient algorithms that can help us gain statistical insight from the large databases that record much of our life. However, as our digital footprint becomes larger, many databases that were originally considered anonymous can now be re-identified. How do we make sure that doesn't happen?
This paper looks at the problem of privacy in the context
of Online Social Networks (OSNs). In particular, it examines the predictability of different types of personal information based on OSN data and compares it to the perceptions of users about the disclosure of their information. To this end, a real life dataset is composed. This consists of the Facebook data (images, posts and likes) of 170 people along with
their replies to a survey that addresses both their personal information, as well as their perceptions about the sensitivity and the predictability of different types of information. Importantly, we evaluate several learning techniques for the prediction of user attributes based on their OSN data. Our analysis shows that the perceptions of users with respect to
the disclosure of specific types of information are often incorrect. For instance, it appears that the predictability of their political beliefs and employment status is higher than they tend to believe. Interestingly, it also appears that information that is characterized by users as more sensitive, is actually more easily predictable than users think, and vice versa (i.e. information that is characterized as relatively less sensitive is less easily predictable than users might have thought).
Similar to Visible Partisanship Convolutional Neural Networks for the Analysis of Political Images (20)
Perceived versus Actual Predictability of Personal Information in Social Netw...
Visible Partisanship Convolutional Neural Networks for the Analysis of Political Images
1. Visible
PartisanshipPolmeth XXXIII, Rice University, July 22, 2016
Convolutional Neural Networks for the Analysis of Political Images
L. Jason Anastasopoulos ljanastas@uga.edu (University of Georgia, Public Admin +
Policy, Political Science, Georgia Informatics Institute)
Dhruvil Badani (UC Berkeley, EECS)
Crystal Lee (UC Berkeley, EECS)
Shiry Ginosar (UC Berkeley, EECS)
2. Outline
▪ Background
▪ Image experiment - “the people you pose with”– how race and gender of
people politicians pose with affect perceptions.
▪ Race classifier for images using convolutional neural networks.
▪ Analysis of race in US House of Representative Facebook profile
photos.
8. Political functions of images
For politicians…
▪ Signaling
▪ Partisanship/ideology.
▪ Policy positions.
▪ Homestyle (Fenno 1978)
▪ Qualification – competence.
▪ Identification – “I am one of you.”
▪ Empathy – “I care about your needs.”
9. Political functions of images
For politicians…
▪ Signaling
▪ Partisanship/ideology.
▪ Policy positions.
▪ Homestyle (Fenno 1978)
▪ Qualification – competence.
▪ Identification – “I am one of you.”
▪ Empathy – “I care about your needs.”
11. Hardware and software limitations
▪ Hardware
▪ Even small images are “big data.”
▪ One 200 x 200 image = 3 200x200
matrices or 1 vector of length
120,000.
12. Hardware and software limitations
▪ Software
▪ High dimensional statistical theory developed more recently.
▪ Asymptotics deals with properties of estimators as with a fixed number of
parameters, p.
▪ In modern machine learning applications,
Introduction
classical asymptotic theory: sample size n → +∞ with number of
parameters p fixed
modern applications in science and engineering:
large-scale problems: both p and n may be large (possibly p ≫ n)
need for high-dimensional theory that allows (n, p) → +∞
Introduction
classical asymptotic theory: sample size n → +∞ with number of
parameters p fixed
modern applications in science and engineering:
large-scale problems: both p and n may be large (possibly p ≫ n)
need for high-dimensional theory that allows (n, p) → +∞
13. Image analysis renaissance in social science
Hardware: Powerful CPUs
and now GPUs in desktop
computers (thanks gamers!)
14. Image analysis renaissance in social science
▪ Software
▪ Statistical theory for computing in high
dimensions.
▪ Advances in numerical computing.
▪ Deep-learning frameworks: Torch,
Tensorflow, Theano, Caffe.
17. Questions
▪ How do the group characteristics (gender, race, age, etc.) of people that
Members of Congress pose with affect how they are perceived?
▪ Social media “homestyle”
▪ Is there evidence that Members of Congress use social media images to signal
identification and empathy with constituents using group characteristics?
18. Questions
▪ How do the group characteristics (gender, race, age, etc.) of people that
Members of Congress pose with affect how they are perceived?
▪ Social media “homestyle”
▪ Is there evidence that Members of Congress use social media images to signal
identification and empathy with constituents using group characteristics?
19. “The people you pose with” experiment: Lou
Barletta
▪ Lou Barletta (R-PA, 11) chosen for initial experiment because of relative obscurity
and similar pictures with different groups of people.
▪ MTurk respondents randomly assigned one of 7 images with Barletta
▪ Alone – Barletta by himself.
▪ Woman – Barletta with a woman.
▪ Man – Barletta with a white man.
▪ Black – Barletta with African-American men.
▪ Asked a series of questions based only on the image.
21. What is your best guess of the political party
that this politician belongs to?
Beliefs about Barletta’s party ID
vary significantly by image shown.
Alone: 39% guessed Democrat
61% guessed Republican
Black: 58% guessed Democrat
42% guessed Republican
Man: 42% guessed Democrat
58% guessed Republican
Woman: 43% guessed Democrat
57% guessed Republican
22. What is your best guess of this politician’s
ideological orientation?
Average by treatment groups
Alone: Moderate.
Black: Liberal.
Man: Moderate.
Woman: Moderate.
23. Does this politician seem…honest and
trustworthy?
Perceived to be more trustworthy
when pictured next to a woman.
24. Does the politician seem…like a strong and
decisive leader?
Perceived to be a stronger leader
when pictured next to a woman.
25. Does the politician seem…knowledgeable about
the issues?
Perceived to be less
knowledgeable when pictured
next to an older white man.
26. Does the politician seem…like someone who
shares my values? (non-white respondents)
Perceived by non-white
respondents to share their
values when pictured next to
African-American men.
27. Barletta experiment conclusions
▪ Opinion of Barletta affected by group identity of individuals included in images.
▪ Race affected beliefs about partisanship/ideology and implied “shared
values.”
▪ Gender affected beliefs in trustworthiness, honesty and decisiveness.
▪ Survey experiment expanding – goal is to test which aspects of photos most
strongly tied to perceptions of candidate ideology and party.
28. Questions
▪ How do the group characteristics (gender, race, age, etc.) of people that
Members of Congress pose with affect how they are perceived?
▪ Social media “homestyle”
▪ Is there evidence that Members of Congress use social media images to signal
identification and empathy with constituents using group characteristics?
29. Questions
▪ How do the group characteristics (gender, race, age, etc.) of people that
Members of Congress pose with affect how they are perceived?
▪ Social media “homestyle”
▪ Is there evidence that Members of Congress use social media images to signal
identification and empathy with constituents using group characteristics?
31. Goals and Methods
▪ Identify race of individuals pictured in Facebook profiles of House Members.
▪ Viola-Jones Algorithm
▪ Train a convolutional neural network race classifier.
▪ Explore how distribution of racial groups in photos compare to congressional
district demographics, partisanship and ideology.
▪ Compare Facebook profile “demographics” with district demographics, party id
and DW-Nominate scores.
32. Results
▪ Democrats and Republicans in the US House of Representatives have very
different social media styles.
▪ Evidence that Democrats use Facebook images to elicit racial identification
and empathy among constituents.
33. How you see an image…
▪ Image as data.
▪ Eg 620x412
pixel image.
You see:
{Donald
Trump, blue
tie, black suit,
blue
background,
anger}
34. How a computer sees an image...
▪ 640x412 pixel
image.
▪ 3 Channels:
Red, Green,
Blue
▪ 3 640x412
matrices of
pixel intensity
values.
▪ -or- 3x640x412
= 791,040 x 1
vector
37. Theoretical means of image feature extraction
limited mostly to faces...
Viola-Jones Object Detection Framework
38. Data driven approach/supervised machine learning
approach – train models utilizing pixel intensity
data...
Collect labeled
images.
Train a machine
learning
classifier.
Test classifier
accuracy.
CIFAR-10 library
of 32x32 labels
images
benchmark
performance.
39. One layer neural network
X1
X2
X3
▪ Inputs multiplied by weights
and added create “hidden”
layer.
▪ Hidden layer passed
through “activation function”
multiplied by another set of
weights to generate class
probabilities/scores.
▪ Simplest model discussed
by psychologist Rosenblatt
(1958)
40. Neural network activation functions
▪ Most common activation
functions are sigmoid and
tangent.
▪ Optimizing predictions
requires
▪ Choice of activation
functions and;
▪ Choice of weights.
41. Backpropagation
▪ Rumelhart, Hinton and Williams (1986)
▪ Selection of weights involves:
▪ Forward pass - Calculation of loss function.
▪ Backward pass – Use of chain rule and stochastic gradient descent to iteratively
calculate new weights.
42. Convolutional neural networks for image feature
classification
Multi-layer neural network involving series of activation functions on chunks of pixel data.
43. Convolutional neural networks for image feature
classification
• Equivalent of
passing pixel data
through a number
of “filters.”
• Discover which
“filter” is activated
by which labeled
image category.
• Output is highest
probability category
given filter
responses
Image credit: Andrej Karpathy
44. Convolutional neural network: building a race
classifier
• Labeled image data
• 60,000 high school yearbook images, 1960-2013
• 6,000 images sampled from Congressional Facebook dataset we collected.
• Categories: White, African-American, East Asian, Hispanic.
• 16-layer CNN model for large-scale image recognition from CNN Model Zoo by
Simonyan and Zisserman (2015): http://arxiv.org/pdf/1409.1556.pdf and
https://gist.github.com/ksimonyan/211839e770f7b538e2d8#file-readme-md
45. Convolutional neural network: building a race
classifier
• Step 1: Identify
faces using Viola-
Jones algorithm.
• Image on the right is
a Facebook photo
from Representative
Tammy Duckworth ‘s
(D-IL) profile.
48. Convolutional neural network: building a race
classifier
• Step 4: Test classifier accuracy
• Avg. cross-validated accuracy rates of 90% for whites, 85% for African-
American, 75% for Asian, 65% for HIspanic.
49. Convolutional neural network: building a race
classifier
• Step 5: Estimate race of individuals in Congressional Facebook image set using
trained model.
50. Race and partisanship in House Facebook
image posts (white House members)
White Democrats post Facebook
photos of …
African-Americans at 4x the rate of
white Republicans
Hispanics at 1.2x the rate of white
Republicans.
Asians at 2x the rate of white
Republicans.
51. Race and partisanship in House Facebook
image posts (white House members)
Even conditional on relevant district
demographics, state and region
fixed effects, evidence of conscious
efforts by partisans to
include/exclude racial groups in
Facebook image posts.
Democrats (white): +6% more
African-Americans in posts.
Republicans (white): +6% more
whites in posts.
52. Identification and empathy: district
demographics and Facebook image posts
Do MCs strategically post photos of
racial groups to engender
identification and empathy from
constituents?
Overall strong evidence that they do.
Strong relationship between % of
racial group in district and % of racial
group posted in Facebook profiles.
53. Identification and empathy: district demographics
and Facebook image posts by party
Strategic use of race in image posts much more evident among Democrats than Republicans
54. Identification and empathy: district demographics
and Facebook image posts by party
Y = % white in Facebook profile photos
White Democrats more
“race conscious” when
posting FB photos.
After conditioning on
state and region fixed effects and
district demographics, Democrats
Facebook photos more likely to reflect
racial/ethnic mix of district.
55. Identification and empathy: district demographics
and Facebook image posts by party
Representation =
% White in Facebook profile photos –
% White in Congressional District
Whites over-represented in
Facebook photos
of white Democrats and
Republicans…
56. Identification and empathy: district demographics
and Facebook image posts by party
Representation =
% Black in Facebook profile photos –
% Black in Congressional District
African-Americans under-represented
in Facebook photos of Republican MCs
by an average of about 3.8%
57. Identification and empathy: district demographics
and Facebook image posts by party
Representation =
% Hispanic in Facebook profile photos
% Hispanic in Congressional District
Hispanics under-represented
In Facebook photos of both parties, more
so among Democrats
58. Identification and empathy: district demographics
and Facebook image posts by party
Representation =
% Asian in Facebook profile photos
% Asian in Congressional District
Asians under-represented in Facebook
photos of white Democrats.
59. Discussion
• Modern computational methods allow for the large scale analysis of
images.
• Here we build a race classifier for images using convolutional neural
networks.
60. Discussion
▪ Characteristics of people that politicians pose with shape
perceptions.
▪ Democrats and Republicans in the US House of Representatives
have very different social media styles.
▪ Evidence that Democrats use Facebook images to elicit racial
identification and empathy among constituents.