50
infervote.org Democratizing democracy: a resource for political engagement Robert Vogel

Final demo

Embed Size (px)

Citation preview

Page 1: Final demo

infervote.org Democratizing democracy: a resource for political engagement

Robert Vogel

Page 2: Final demo

Why?

• We are constantly bombarded with political rhetoric that shape our political views.

• How are we ACTUALLY represented by our elected officials?

• How does and will our congress vote on topics we care about?

• Do senator voting records exhibit polarized behavior? • How can we find misbehaving and polarized senators? • What action can we take?

Page 4: Final demo

The Polarity Index

Senator i Votes

Republican Senator j

Votes

Page 5: Final demo

The Polarity Index

Senator i Votes

Republican Senator j

VotesVotes in common

Page 6: Final demo

The Polarity Index

Senator i Votes

Republican Senator j

VotesVotes in common

Jij =Votes in common

All votes

Page 7: Final demo

The Polarity Index

Senator i Votes

Republican Senator j

VotesVotes in common

Jij =Votes in common

All votes

Ji1 = ~1

Page 8: Final demo

The Polarity Index

Senator i Votes

Republican Senator j

VotesVotes in common

Jij =Votes in common

All votes

Ji1 = ~1

Ji2 =

+

~0

Page 9: Final demo

The Polarity Index

Senator i Votes

Republican Senator j

VotesVotes in common

Jij =Votes in common

All votes

+

Polarity=

Ji1 = ~1

Ji2 =

+

~0

Page 10: Final demo

The Polarity Index

Senator i Votes

Republican Senator j

VotesVotes in common

Jij =Votes in common

All votes

+

Polarity=

Ji1 = ~1

Ji2 =

+

~0

Page 11: Final demo

Clustering Senator Voting with Jaccard distance

Page 12: Final demo

Democrat RepublicanInd

Clustering Senator Voting with Jaccard distance

Page 13: Final demo

Democrat RepublicanInd

Clustering Senator Voting with Jaccard distance

dMitch McConnell (KY)John McCain (AZ)

Page 14: Final demo

Democrat RepublicanInd

Clustering Senator Voting with Jaccard distance

Elizabeth Warren (MA)

Dianne Feinstein (CA)

dMitch McConnell (KY)John McCain (AZ)

Page 15: Final demo

Democrat RepublicanInd

Clustering Senator Voting with Jaccard distance

Elizabeth Warren (MA)

Dianne Feinstein (CA)Bernie Sanders (VT)

dMitch McConnell (KY)John McCain (AZ)

Page 16: Final demo

Democrat RepublicanInd

Clustering Senator Voting with Jaccard distance

Elizabeth Warren (MA)

Dianne Feinstein (CA)Bernie Sanders (VT)

dMitch McConnell (KY)John McCain (AZ)

Rand Paul (KY) Marco Rubio (FL) Ted Cruz (TX)

Page 17: Final demo

Democrat RepublicanInd

Clustering Senator Voting with Jaccard distance

Elizabeth Warren (MA)

Dianne Feinstein (CA)Bernie Sanders (VT)

dMitch McConnell (KY)John McCain (AZ)

Rand Paul (KY) Marco Rubio (FL) Ted Cruz (TX)

Page 18: Final demo

Do votes align with bill sponsors?

Republican Sponsor

• The bill sponsor is the member of congress that introduces the document for consideration.

Democrat Sponsor

Page 19: Final demo

Infer directionality of biochemical reactions using Langevin dynamics

Robert Vogel

Developed new parameterization of therapeutic drugs using insight from nonlinear dynamical systems

Page 20: Final demo

Voting Distributions and the Simulated Senate• Sample 5000 experimental senates using parameters from data

• Data exhibit a more diverse distribution then simulation

• Potential next step, use the Ising model to model pairwise interactions

Republican SponsorDemocrat Sponsor

Page 21: Final demo

The Jaccard Index and Political Polarity

Page 22: Final demo

Jaccard Index for Measuring Polarity

• Jaccard Index measures the number identical votes between Senator i and Senator j normalized to total votes

• Polarity index is the average Jaccard index between Senator i and all Senators in party R.

Jij =|vi \ vj ||vi [ vj |

JiR =1

NR

X

j2R

Jij

Page 23: Final demo

Distribution of polarity index

• If party politics were not a factor, these distributions would overlap

Page 24: Final demo

Jaccard Distance for Senator Clustering

• Jij 1 the more similar Senator i votes to Senator j.

• Hierarchical clustering utilizes a dissimilarity measure. Standard solution 1 - Jij

dJ(i, j) = 1� |vi \ vj ||vi [ vj || {z }

Jij

Page 25: Final demo

Votes are strictly partisan

• Fraction of votes along party line, most votes are partisan

Page 26: Final demo

Topic Modeling

Page 27: Final demo

Topic modeling of legislative summariesW

ord

spac

e pe

r bill

Topi

c Sp

ace

Bills

Topi

cs

T S = S’

Y N0

Congress person Topic Probabilities

P

T’ = P’

New bill in topic space Probability of vote

P

Y

N0

Prediction

Clustering

Page 28: Final demo

Can we make predictions of senator votes from legislative documents?

Topic 1

Topic 2

Topic 3

Senator 1 Vote

Document 1

Document 2

Document NTopic M

Page 29: Final demo

Can we make predictions of senator votes from legislative documents?

Topic 1

Topic 2

Topic 3

Senator 1 Vote

Document 1

Document 2

Document NTopic M

VoteSenator 2

Page 30: Final demo

Can we make predictions of senator votes from legislative documents?

Topic 1

Topic 2

Topic 3

Senator 1 Vote

Document 1

Document 2

Document NTopic M Senator L Vote

VoteSenator 2

Page 31: Final demo

Legislative document reduction to topics

• 2559 legislative summaries

• Constructed 6403 word basis from text by:

• removing stop words (e.g and, that, this, a)

• removing non-english words

• stemming (e.g. rested equal to rest)

• TF-IDF

• Cosine similarity to group topics

Page 32: Final demo

Legislative document reduction to topics

• 2559 legislative summaries

• Constructed 6403 word basis from text by:

• removing stop words (e.g and, that, this, a)

• removing non-english words

• stemming (e.g. rested equal to rest)

• TF-IDF

• Cosine similarity to group topics

• Result: No structure in bill data, more data needed!

Documents

Documents

Page 33: Final demo

Document dimensionality reduction not sufficient with PCA

95% of the variablity corresponds to > 1000 dimensions

A small topic space, represents a small portionof the variability

Page 34: Final demo

tSNE dimensionality reduction suggests no structure in bill data

• Each point is a document in the reduced space defined by tSNE

• t-distributed Stochastic Neighborhood Embedding maps points from a high to a low dimensional space by minimizing the Kullback-Leibler Divergence (minimize information loss).

Page 35: Final demo

The data

Page 36: Final demo

Why only choose Bills and Amendments?

• In general, these documents can become law

• Other votes are for approving nominations for office and resolutions.

• Resolutions can be very diverse as shown below.

Page 37: Final demo

Graduate Research: An overview

• Langevin Dynamics to:

• figure out direction in biochemical reactions, and

• testing isolation of a network motif.

• Bifurcation analysis to identify:

• nodes in a network sensitive to therapeutic inhibition

Page 38: Final demo

Biochemical Noise

• Flow cytometry measures the relative quantity of <= 12 biochemical species per cell at a rate of 20,000 cells per second.

• Fluorescent molecules are coupled to antibodies that specifically bind to a biochemical species.

• Quantity of molecules is proportional to fluorescent signal

−2 −1 0 1 2−4

−3

−2

−1

0

1

2

3

4

PMA 1

PMA 2

PMA 3

Log2 Normalized pMEK Log

2 N

orm

aliz

ed p

pER

K

PMA 1

PMA 2

PMA 3

PMA 1

PMA 2

PMA 3

−2 −1 0 1 2−4

−3

−2

−1

0

1

2

3

4

PMA : 1

Log2 pMEK

Log 2

ppE

RK

PMA : 1

−2 −1 0 1 2−4

−3

−2

−1

0

1

2

3

4

PMA : 2

Log2 pMEK

Log 2

ppE

RK

PMA : 2

−2 −1 0 1 2−4

−3

−2

−1

0

1

2

3

4

PMA : 3

Log2 pMEK

Log 2

ppE

RK

PMA : 3

Page 39: Final demo

Fluctuations break symmetry of average measurements

Variance of Y > XY

X𝜉x

𝜉y

O

O

• Fluctuations from source node propagates to target

X

Y𝜉y

𝜉x

O

OVariance of X > Y

True Model False Model

Page 40: Final demo

Fluctuations break symmetry of average measurements

Variance of Y > X

0.2 0.3 0.4 0.5 0.60.2

0.4

0.6

0.8

1

1.2

1.4

1.6

Cov(pMEK, ppERK)

Varia

nce

True Model

pMEKppERK

0.2 0.3 0.4 0.5 0.60.2

0.4

0.6

0.8

1

1.2

1.4

1.6

Cov(pMEK, ppERK)

Varia

nce

False Model

pMEKppERK

0.2 0.3 0.4 0.5 0.60.2

0.4

0.6

0.8

1

1.2

1.4

1.6

Cov(pMEK, ppERK)

Varia

nce

True Model

pMEKppERK

0.2 0.3 0.4 0.5 0.60.2

0.4

0.6

0.8

1

1.2

1.4

1.6

Cov(pMEK, ppERK)

Varia

nce

False Model

pMEKppERK

Y

X𝜉x

𝜉y

O

O

• Fluctuations from source node propagates to target

X

Y𝜉y

𝜉x

O

OVariance of X > Y

True Model False Model

Page 41: Final demo

Nonlinear dynamics of biochemical inhibition

Page 42: Final demo

Inhibition of biochemical signaling in cells, a new parameter 𝛼

L c SRC

pMEK MEKi

ppERK

In preparation for publicationChemical SpeciesChemical Complex Enzymatic reaction Enzymatic Inhibition

Page 43: Final demo

Inhibition of biochemical signaling in cells, a new parameter 𝛼

L c SRC

pMEK MEKi

ppERK

L c SRC

SRCi

pMEK

ppERK

In preparation for publicationChemical SpeciesChemical Complex Enzymatic reaction Enzymatic Inhibition

Page 44: Final demo

Inhibition of biochemical signaling in cells, a new parameter 𝛼

L c SRC

pMEK MEKi

ppERK

L c SRC

SRCi

pMEK

ppERK

In preparation for publicationChemical SpeciesChemical Complex Enzymatic reaction Enzymatic Inhibition

Page 45: Final demo

Inhibition of biochemical signaling in cells, a new parameter 𝛼

L c SRC

pMEK MEKi

ppERK

L c SRC

SRCi

pMEK

ppERK

In preparation for publicationChemical SpeciesChemical Complex Enzymatic reaction Enzymatic Inhibition

Page 46: Final demo

Nonlinear dynamics of biochemical inhibition in cells

Chemical Species

Chemical Complex

Enzymatic reaction

Enzymatic Inhibition

In preparation for publication

Page 47: Final demo

Nonlinear dynamics of biochemical inhibition in cells

Chemical Species

Chemical Complex

Enzymatic reaction

Enzymatic Inhibition

L c SRC

pMEK MEKi

ppERK

[MEKi] [MEKi]

In preparation for publication

Page 48: Final demo

Nonlinear dynamics of biochemical inhibition in cells

Chemical Species

Chemical Complex

Enzymatic reaction

Enzymatic InhibitionL c SRC

SRCi

pMEK

ppERK

[SRCi] [SRCi]

L c SRC

pMEK MEKi

ppERK

[MEKi] [MEKi]

In preparation for publication

Page 49: Final demo

Finding dysfunctional components in tumor samples

Page 50: Final demo

Single cell measurements find abnormalities in tumor patient profiles• Kullback-Leibler divergence measures the dissimilarity of the single cell

distribution of biochemical signaling features between patient and healthy donor samples.

Sjk =

X

i2HD

DKL (Pj(xk)||Pi(xk))

=

X

i2HD

Pj(xk) log

✓Pj(xk)

Pi(xk)

• k = Biochemical species

• j = patient id

• i = Healthy donor