This is a guest post by Randy Zwitch (@randyzwitch), a digital analytics and predictive modeling consultant in the Greater Philadelphia area. Randy blogs regularly about Data Science and related technologies at http://randyzwitch.com. He’s blogged at Bad Hessian before here.

WordPress Stats - Visitors vs. Views
WordPress Stats – Visitors vs. Views

For those of you with WordPress blogs and have the Jetpack Stats module installed, you’re intimately familiar with this chart. There’s nothing particularly special about this chart, other than you usually don’t see bar charts with the bars shown superimposed.

I wanted to see what it would take to replicate this chart in R, Python and Julia. Here’s what I found. (download the data).

Continue reading

This is a guest post by Monica Lee and Dan Silver. Monica is a Doctoral Candidate in Sociology and Harper Dissertation Fellow at the University of Chicago. Dan is an Assistant Professor of Sociology at the University of Toronto. He received his PhD from the Committee on Social Thought at the University of Chicago.

For the past few months, we’ve been doing some research on musical genres and musical unconventionality.  We’re presenting it at a conference soon and hope to get some initial feedback on the work.

This project is inspired by the Boss, rock legend Bruce Springsteen.  During his keynote speech at the 2012 South-by-Southwest Music Festival in Austin, TX, Springsteen reflected on the potentially changing role of genre classifications for musicians.  In Springsteen’s youth, “there wasn’t much music to play.  When I picked up the guitar, there was only ten years of Rock history to draw on.”  Now, “no one really hardly agrees on anything in pop anymore.”  That American popular music lacks a center is evident in a massive proliferation in genre classifications:

“There are so many sub–genres and fashions, two–tone, acid rock, alternative dance, alternative metal, alternative rock, art punk, art rock, avant garde metal, black metal, Christian metal, heavy metal, funk metal, bland metal, medieval metal, indie metal, melodic death metal, melodic black metal, metal core…psychedelic rock, punk rock, hip hop, rap rock, rap metal, Nintendo core [he goes on for quite a while]… Just add neo– and post– to everything I said, and mention them all again. Yeah, and rock & roll.”

Continue reading

This is a guest post by Neal Caren. He is an Associate Professor of Sociology at the University of North Carolina, Chapel Hill. He studies social movements and the media.

Folks like Jay Ulfelder and Erin Simpson have already pointed out the flaws in Mona Chalabi’s recent stories that used GDELT to count and map the number of kidnappings in Nigeria. I don’t have much to add, except to point out that hints to some of the problems with using the data to count events were in the dataset all along.

In the first story, “Kidnapping of Girls in Nigeria Is Part of a Worsening Problem,” Chalabi writes:

The recent mass abduction of schoolgirls took place April 15; the database records 151 kidnappings on that day and 215 the next.

To investigate the source of this claim, I downloaded the daily GDELT files for those days and pulled all the kidnappings (CAMEO Code 181) that mentioned Nigeria. GDELT provides the story URLs. Each different GDELT event is assocaited with a URL, although one article can produce more than one GDELT event.

I’ve listed the URLs below. Some of the links are dead, and I haven’t looked at all of the stories yet, but, as far as I can tell, every single story that is about a specific kidnapping is about the same event. You can get a sense of this by just look at the words in the URLS for just those two days. For example, 89 of the URLs contain the word “schoolgirl” and 32 contain Boko Haram. It looks like instead of 366 different kidnappings, there were many, many stories about one kidnapping.

Something very strange is happening with the way the stories are parsed and then aggregated. I suspect that this is because when reports differ on any detail, each report is counted as a different event. Events are coded on 57 attributes each of which has multiple possible values and it appears that events are only considered duplicates when they match all on attributes. Given the vagueness of events and variation in reporting style, a well-covered, evolving event like the Boko Haram kidnapping is likely to covered in multiple ways with varying degrees of specificity, leading to hundreds of “events” from a single incident.

Plotting these “events” on a map only magnifies the errors–there are 41 different unique latitudes/longitudes pairs listed to described the same abduction.

At a minimum, GDELT should stop calling itself an “event” database and call itself a “report” database. People still need to be very careful about using the data, but defaulting to writing that there were 366 reports about kidnapping in Nigeria over these two days is much more accurate than saying there were 366 kidnappings.

In case you were wondering, GDELT lists 296 abductions associated with Nigeria that happened yesterday (May 14th, 2014) in 42 different locations. Almost all of the articles are about the Boko Haram school girl kidnappings, and the rest are entirely miscoded, like the Heritage blog post about how the IRS is targeting the Tea Party.

Continue reading

This is a guest post by Charles Seguin. He is a PhD student in sociology at the University of North Carolina at Chapel Hill.

Sociologists and historians have shown us that national public discourse on lynching underwent a fairly profound transformation during the periods from roughly 1880-1925. My dissertation studies the sources and consequences of this transformation, but in this blog post I’ll just try to sketch some of the contours of this transformation. In my dissertation I use machine learning methods to analyze this discursive transformation, however after reading several hundred lynching articles to train the machine learning algorithms, I think I have a pretty good understanding of key words and phrases that mark the changes in lynching discourse. In this blog post then, I’ll be using basic keyword, bigram (word pair), and trigram searches to illustrate some of the changes in lynching discourse.

Continue reading

This is a guest post by Laura K. Nelson. She is a doctoral candidate in sociology at the University of California, Berkeley. She is interested in applying automated text analysis techniques to understand how cultures and logics unify political and social movements. Her current research, funded in part by the NSF, examines these cultures and logics via the long-term development of women’s movements in the United States. She can be reached at lknelson3@berkeley.edu.

Computer-assisted, or automated, text analysis is finally making its way into sociology, as evidenced by the new issue of Poetics devoted to one technique, topic modeling (Poetics 41, 2013). While these methods have been widely used and explored in disciplines like computational linguistics, digital humanities, and, importantly, political science, only recently have sociologists paid attention to them. In my short time using automated text analysis methods I have noticed two recurring issues, both which I will address in this post. First, when I’ve presented these methods at conferences, and when I’ve seen others present these methods, the same two questions are inevitably asked and they have indeed come up again in response to this issue (more on this below). If you use these methods, you should have a response. Second, those who are attempting to use these methods often are not aware of the full range of techniques within the automated text analysis umbrella and choose a method based on convenience, not knowledge.

Continue reading

This is a guest post by Randy Zwitch (@randyzwitch), a digital analytics and predictive modeling consultant in the Greater Philadelphia area. Randy blogs regularly about Data Science and related technologies at http://randyzwitch.com.

A few months ago I passed the 10-year point in my analytics/predictive modeling career. While ‘Big Data’ and ‘Data Science’ have only become buzzwords in recent years, hitting the limit on computing resources has been something that has plagued me throughout my career. I’ve seen this problem manifest itself in many ways, from having analysts get assigned multiple computers for daily work, to continuously scraping together budget for more processors on a remote SAS server and spending millions on large enterprise databases just to get processing of data below a 24-hour window.

Luckily, advances in open source software & cloud computing have driven down the cost of data processing & analysis immensely. Using IPython Notebook along with Amazon EC2, you can now procure a 32-core, 60GB RAM virtual machine for roughly $0.27/hr (using a spot instance). This tutorial will show you how to setup a cluster instance at Amazon, install Python, setup IPython as a public notebook server and access this remote cluster via your local web browser.

To get started with this tutorial, you need to have an Amazon Web Services account. I also assume that you already have basic experience interacting with computers via the command line and know about IPython. Basically, that you are the average Bad Hessian reader…

Continue reading

This is a guest post by Karissa McKelvey. She has a BA in Computer Science and Political Science from Indiana University. After graduating, she worked as a research assistant at the Center for Complex Networks and Systems Research at Indiana University on an NSF grant to analyze and visualize the relationship between social media expressions and political events. She is an active contributor to open source projects and continues to publish in computer supported cooperative work and computational social science venues. She currently works as a Software Engineer at Continuum Analytics.

Imagine you are a graduate student of some social or behavioral science (not hard, I assume). You want to collect some data: say I’m going to study the fluctuation of value of products over time on Craiglist, or ping the Sunlight Foundation’s open government data, or use the GDELT to study violent political events. There are a variety of tools I may end up using for my workflow:

  1. Retrieving the data: Python, BeautifulSoup
  2. Storing the data: CSV, Json, MySQL, MongoDB, bash
  3. Retrieving this stored data: SQL, Hive, Hadoop, Python, Java
  4. Manipulating the data: Python, CSV, R
  5. Running regressions, simulations: R, Python, STATA, Java
  6. Presenting the data: R, Excel, Powerpoint, Word, LaTeX

My workflow for doing research now requires a variety of tools, some of which I might have never used before. The number of tools I use seems to scale with the amount of work I try to accomplish. When I encounter a problem in my analysis, or can’t reproduce some regression or simulation I ran, what happened? Where did it break?

Should it really be this difficult? Should I really have to learn 10 different tools to do data analysis on large datasets? We can look at the Big Data problem in a similar light as surveys and regression models. The largest and most fundamental part of the equation is just that this stuff is new – high-priority and well thoughout workflows have yet to be fully developed and stablized.

What if I told you that you could do all of this with the fantastically large number of open source packages in Python? In your web browser, on your iPad?

Continue reading

This is a guest post by Jen Schradie. Jen is a doctoral candidate in the Department of Sociology at the University of California-Berkeley and the Berkeley Center for New Media. She has a master’s degree in sociology from UC Berkeley and a MPA from the Harvard Kennedy School. Using both statistical methods and qualitative fieldwork, her research is at the intersection of social media, social movements and social class. Her broad research agenda is to interrogate digital democracy claims in light of societal and structural differences. Before academia, she directed six documentary films on social movements confronting corporate power. You can find her at www.schradie.com or @schradie on Twitter.

Five years ago, Chris Anderson, editor-in-chief of Wired Magazine, wrote a provocative article entitled, “The End of Theory: The Data Deluge Makes the Scientific Method Obsolete” (2008). He argued that hypothesis testing is no longer necessary with google’s petabytes of data, which provides all of the answers to how society works. Correlation now “supercedes” causation:

This is a world where massive amounts of data and applied mathematics replace every other tool that might be brought to bear. Out with every theory of human behavior, from linguistics to sociology. Forget taxonomy, ontology, and psychology. Who knows why people do what they do? The point is they do it, and we can track and measure it with unprecedented fidelity. With enough data, the numbers speak for themselves.

An easy strawman, Anderson’s piece generated a host of articles in academic journals decrying his claim. The overall consensus, to no surprise, was that the scientific method – i.e. hypothesis testing – is far from over. Most argued as Pigliucci (2009:534) articulated,

But, if we stop looking for models and hypotheses, are we still really doing science? Science, unlike advertising, is not about finding patterns—although that is certainly part of the process—it is about finding explanations for those patterns.

Other analysts focused on the debate around “correlation is not causation.” Some critiqued Anderson in that correlation can lead you in the wrong direction with spurious noise.  Others implicitly pointed to what Box (1976) articulated so well pre-Big Data – that science is an iterative process in which correlation is useful in that it can trigger research which uses hypothesis testing.

Continue reading

datagothamThis is a guest post by Sean J. Taylor, a PhD student in Information Systems at NYU’s Stern School of Business.

Last Thursday and Friday I attended the 2nd annual DataGotham conference in New York City. Alex Hanna asked me to write about my experience there for the benefit of those who were unable to attend, so here’s my take on the event.

Thursday evening was a social event in a really sweet rooftop space in Tribeca with an open bar and great food (a dangerous combination for this still-grad-student). Though I spent a lot of the time catching up with old friends, I would describe the evening as “hanging out on Twitter, but in person.” I met no fewer than a dozen people I had only previously known online. I am continually delighted at how awesomeness on Twitter is a reliable indicator of awesomeness in-person. Events like DataGotham are often worth it for this reason alone.

Continue reading

This is a guest post by John Beieler, originally posted at http://johnbeieler.org/blog/2013/04/12/gdelt/

I made the remark on Twitter that it seemed like GDELT week due to a Foreign Policy piece about the dataset, Phil and Kalev’s paper for the ISA 2013 meeting, and a host of blog posts about the data. So, in the spirit of GDELT week, I thought I would throw my hat into the ring. But instead of taking the approach of lauding the new age that is approaching for political and social research due to the monstrous scale of the data now available, I thought I would write a little about the issues that come along with dealing with such massive data.

Dealing with GDELT

As someone who has spent the better part of the past 8 months dealing with the GDELT dataset, including writing a little about working with the data, I feel that I have a somewhat unique perspective. The long and the short of my experience is: working with data on this scale is hard. This may strike some as obvious, especially given the cottage industry that has sprung up around Hadoop and and other services for processing data. GDELT is 200+ million events spread across several years. Each year of the reduced data is in a separate file and contains information about many, many different actors. This is part of what makes the data so intriguing and useful, but the data is also unlike data such as the ever-popular MID data in political science that is easily managed in a program like Stata or R. The data requires subsetting, massaging, and aggregating; having so much data can, at some points, become overwhelming. What states do I want to look at? What type of actors? What type of actions? What about substate actors? Oh, what about the dyadic interactions? These questions and more quickly come to the fore when dealing with data on this scale. So while the GDELT data offers an avenue to answer some existing questions, it also brings with it many potential problems.

Careful Research

So, that all sounds kind of depressing. We have this new, cool dataset that could be tremendously useful, but it also presents many hurdles. What, then, should we as social science researchers do about it? My answer is careful theorizing and thinking about the processes under examination. This might be a “well, duh” moment to those in the social sciences, but I think it is worth saying when there are some heralding “The End of Theory”. This type of large-scale data does not reduce theory and the scientific method to irrelevance. Instead, theory is elevated to a position of higher importance. What states do I want to look at? What type of actions? Well, what does the theory say? As Hilary Mason noted in a tweet:

Data tells you whether to use A or B. Science tells you what A and B should be in the first place.

Put into more social-scientific language, data tells us the relationship between A and B, while science tells us what A and B should be and what type of observations should be used. The data under examination in a given study should be driven by careful consideration of the processes of interest. This idea should not, however, be construed as a rejection of “big data” in the social sciences. I personally believe the exact opposite; give me as many features, measures, and observations as possible and let algorithms sort out what is important. Instead, I think the social sciences, and science in general, is about asking interesting questions of the data that will often require more finesse than taking an “ANALYZE ALL THE DATA” approach. Thus, while datasets like GDELT provide new opportunities, they are not opportunities to relax and let the data do the talking. If anything, big data generating processes will require more work on the part of the researcher than previous data sources.

John Beieler is a Ph.D. student in the Department of Political Science at Pennsylvania State University. Additionally, he is a trainee in the NSF Big Data Social Science IGERT program for 2013-2015. His substantive research focuses on international conflict and instances of political violence such as terrorism and substate violence. He also has interests in big data, machine learning, event forecasting, and social network analysis. He aims to bring these substantive and methodological interests together in order to further research in international relations and enable greater predictive accuracy for events of interest.