What Does a Political Networks Conference Do? (On Twitter)

Last week I mapped the Twitter follow network of those attending the Political Networks Conference in Boulder, CO.  I gathered this data prior to the first day of the conference, so I decided to take a second look now that the conference is over.

Political Networks Twitter Follow Network – Post Conference (Click image for larger version.)

How does the post-conference graph differ from the pre-conference graph?

• The first notable difference is the addition of 18 new nodes.  The size of the network grew by over 50% as new Twitter users decided to follow @PolNetworks during the conference.
• Another difference is the addition of 215 new follow edges.  With only 181 edges in the original graph, the number of follow relationships in the network grew more than 100%.
• The account with the biggest increase in followers was @krmckelv.  Karissa went from only 1 follower to 8.  (She has since changed her Twitter handle to @karissamckelvey.)

Now let’s limit the post-conference graph to a subgraph containing only those nodes that were also in the pre-conference graph.  How has this component changed?

Graph Density: Increased 0.03 from 0.15 to 0.18.

Graph Transitivity:  Decreased 0.03 from 0.56 to 0.53.

Graph Efficiency:  Decreased 0.02 from 0.87 to 0.85.

So new follow edges were added (density), but in a way that more incomplete than complete triangles were formed (transitivity).  Not surprisingly, the new ties were redundant in connecting the graph, lowering efficiency.

Here are some individual-level statistics for the interested.  It was great to get to know many of you at the conference, and I’ll see you at the next one!

Account	In Degree	Out Degree	Eig. Centrality
JaciKettler	10	20	0.3
smotus	35	18	0.27
kwcollins	20	19	0.27
burtmonroe	15	17	0.26
therriaultphd	20	18	0.24
BrendanNyhan	31	17	0.24
JohnCluverius	8	13	0.22
RebeccaHannagan	4	12	0.21
ianpcook	7	12	0.2
Student	27	14	0.2
jlove1982	7	11	0.2
KyleLSaunders	9	13	0.19
krmckelv	12	17	0.19
JeffGulati	9	12	0.18
richardmskinner	8	10	0.15
James_H_Fowler	8	11	0.15
prisonrodeo	16	9	0.15
archimedino	5	10	0.14
davekarpf	7	8	0.13
NateMJensen	5	8	0.13
jon_m_rob	0	8	0.13
sissenberg	8	7	0.12
3876	7	8	0.12
hsquared47	3	7	0.12
marioguerrero	1	7	0.12
FHQ	17	7	0.11
heathbrown	4	8	0.11
First_Street	1	7	0.1
98percentright	5	6	0.1
davidlazer	17	5	0.07
GeoffLorenz	0	5	0.07
jasonjones_jjj	4	6	0.06
matthewhitt	2	4	0.06
DocPolitics	1	4	0.06
JoeLenski	2	4	0.05
maizeandblue	1	4	0.05
allenlinton2	2	3	0.04
DryHeathen	0	4	0.04
ajungherr	0	4	0.04
slimbock	0	2	0.03
cassyld	2	2	0.02
PolNetworks	52	1	0.02
rmbond15	2	3	0.02
DominikBatorski	0	2	0.01
vatrafilm	0	1	0
janschulz	0	1	0
dogaker	0	1	0
stefanjwojcik	1	1	0
KenneyMkenney	0	1	0
ophastings	0	1	0
jbrittaq	0	1	0
jboxstef	1	1	0
Hirschi5	0	1	0

Download edge list as .xlsx: polnetworks2_edge_list

A Dynamic Ordinal Item Response Theory Model with Application to Human Rights Data

by Chris Fariss

Keith Schnakenberg and I continue work on a paper in which we develop a measure the unobservable level of respect for human rights. I blogged about it earlier here. In the new version of the paper we build upon existing insights in the Bayesian measurement literature to develop a dynamic ordinal item-response (DO-IRT) model. We then assess the validity of the estimates obtained from the latent variable generated from the DO-IRT model with the estimates from an ordinal item-response (O-IRT) model and the original additive human rights scales. Below is a plot of the estimates of the latent physical integrity variable (see the paper for a similar plot of latent empowerment variable):

R function for sorting NAs and data in each row of a Matrix

by Chris Fariss

# —– naSortMatrix function —————————— #
# —– by Chris Fariss ———————————— #
#
# Takes a data frame or matrix as an argument
# and returns another matrix after moving any NAs
# within each matrix row to the right of the data
# in that row without changing the order of the
# data. Also calculates the time taken to complete
# the sort and saves it as a global variable:
# naSortMatrix.time
#
# Just copy and paste this during an R session to
# use the function
#
# ——————————————————– #

Acquisition of Social Network Structure

by Jason J. Jones

On Tuesday at the HNG meeting I’ll be discussing three experiments I’ve conducted on the acquisition of social network structure. For a preview, you can read my submission to CogSci 2011 which discusses one of the experiments.

The New Science of Culturomics

By Yunkyu Sohn

Using a corpus of digitalized texts of The Google Books Project (i.e. the offline version of Google Trends), Michel et al. (2011) propose a new approach for quantitative investigation of culture. Their method may have broad impacts on various disciplines such as “lexicography, the evolution of grammar, collective memory, the adoption of technology, the pursuit of fame, censorship, and historical epidemiology.”

A Beautiful Image of the Global Social Network

by James Fowler

We should do one of these for the picture friend network!  Read about the image here.

Game Theory of Mind

by Yunkyu Sohn

Traditional game theory assumes that the level of recursive belief inference is infinite when people choose their strategy as a result of guessing the others’ strategies. For example, in Keynesian beauty contest where all participants are asked to pick a number between 0 and 100 and win if one is the closest to 2/3 of population average, Nash equilibrium predicts all players should chose 0 since recursive inference about others’ preference will decrease the value of your choice, and eventually reach the minimum possible value. However studies in behavioral economics have found that the degree of recursion is bounded to smaller values.

By running a 2 dimensional stag-hunt game, recent fMRI experimental study done by Yoshida et al. demonstrates that people vary their level of inference depending on their partner’s past strategic profiles. Imaging result shows that prefrontal cortex region is subdivided by its roles for encoding uncertainty of inference of partner’s strategy and inferring the degree of recursive inference.