In our paper Law as a Seamless Web, we offer a first-order method to generate case-to-case and opinionunit-to-opinionunit semantic networks. As constructed in the figure above, nodes represent cases decided between 1791-1865 while edges are drawn when two cases possess a certain threshold of semantic similarity. Except for the definition of edges, the process of constructing the semantic graph is identical to that of the citation graph we offered in the prior post. While computer science/computational linguistics offers a variety of possible semantic similarity measures, we choose to employ a commonly used measure. Here a description from the paper:
“Semantic similarity measures are the focus of significant work in computational linguistics. Given the scope of the dataset, we have chosen a first-order method for calculating similarity. After lemmatizing the text of the case with WordNet, we store the nouns with the top N frequencies for each case or opinion unit. We define the similarity between two cases or opinion units A and B as the percentage of words that are shared between the top words of A and top words of B.
An edge exists between A and B in the set of edges if σ (A,B) exceeds some threshold. This threshold is the minimum similarity necessary for the graph to represent the presence of a semantic connection.”
As this a technical paper, it is slanted toward demonstrating proof of methodological concept rather than covering significant substantive ground. With that said, we do offer a hint of our broader substantive goal of detecting the spread of legal concepts between various topical domains. Specifically, with respect to enriching positive political theory, we believe union, intersect and compliment of the semantic and citation networks are really important. More on this point is forthcoming in a subsequent post…
Several months ago, I put together this syllabus for use in a future seminar course Law as a Complex System. This contains far more content than would be practical for the typical 2 credit seminar. However, I have decided to repost this because it could also serve as a reading list for anyone who is interested in learning more about the methodological tradition from which must of our scholarship is drawn. If you see any law related scholarship you believe should be included please feel free to email me.
We have recently posted Law as a Seamless Web? Comparison of Various Network Representations of the United States Supreme Court Corpus (1791-2005) to the SSRN. Given this is the first of several posts about the paper, I will speak broadly and leave details for a subsequent post. From the abstract “As research of judicial citation and semantic networks transitions from a strict focus on the structural characteristics of these networks to the evolutionary dynamics behind their growth, it becomes even more important to develop theoretically coherent and empirically grounded ideas about the nature of edges and nodes. In this paper, we move in this direction on several fronts …. Specifically, nodes represent whole cases or individual ‘opinion units’ within cases. Edges represent either citations or semantic connections.” The table below outlines several possible network representations for the USSC corpus.
The goal of the paper is to do some technical and conceptual work. It is a small slice of broader project with James Fowler (UCSD) and James Spriggs (WashU). We recently presented findings from the primary project at the Networks in Political Science Conference. The main project is entitled The Development of Community Structure in the Supreme Court’s Network of Citations and we hope to have a version of this paper on the SSRN soon. In the meantime, we plan additional discussion of Law as a Seamless Web in the days to come.
We genuinely enjoyed our trip to Boston for the Networks in Political Science 2009 Conference at Harvard. There were many highlights but given the timely nature of their work we wanted to highlight the presentation by John Kelly & Bruce Etling entitled Mapping Culture, Politics, and Religion in the Arabic Blogosphere. This is a followup to last year’s presentation, Mapping Iran’s Online Public: Politics and Culture in the Persian Blogosphere. As usual, the folks at the Berkman Center are doing great work. Check out today’s New York Times featuring an article entitled Iranian Blogosphere Tests Government’s Limits.
It was a long trip but we are looking forward to an exciting day of presentations at tomorrow’s Harvard Political Networks Conference. Check out the program! We hope to see you there.
Live from Barcelona, we are on the road at the International Association for Artificial Intelligence and Law. Henry Prakken has just delivered the keynote address and we will soon be giving our presentation. The conference is interesting as it embraces a wide range of topics and intellectual traditions. For example, there is a significant emphasis on ontological reasoning, computational models of argumentation and the use of XML schemas. In addition, there are a number of folks using graph theoretic techniques and applying them to the development of the law. It has been a nice few days and we have enjoyed our time here. Tomorrow, the trip continues….
We just finished a few very interesting days at Colorado Law School. Given the intersect of Computer Program and Law is a fairly narrow set, it was great to spend sometime time at CU Law School because its faculty features two scholars with a significant programming background — Paul Ohm and Harry Surden.
In addition to discussing CLS, we participated in a workshop on New Institutional Economics (NIE) and Law. I found this workshop very interesting as outside of my work in Computational Legal Studies, I have authored scholarship at the crossroads of New Institutionalism and Constitutional Political Economy. For example, I have this article and this work in progress. My work follows the tradition of the Bloomington School of NIE. In two weeks, I will be presenting work in progress at ISNIE in Berkeley.
Following the Colorado NIE Workship, we participated in the Silicon Flatirons Government 3.0 roundtable. I do not want to preempt the forthcoming white paper but I will say that it was a very worthwhile discussion. It solidified my views on some topics and changed my mind on some others. So, the road show continues… AI & Law in Barcelona starts tomorrow… so light blogging for the next week. But as I like to say… more to come…
Here is a cool visual for the Martin-Quinn Scores. For those of you not familiar, the Martin-Quinn paper and “MQ Scores” represented a significant breakthrough in the field of judicial politics. On that note, Stephen Jessee & Alexander Tahk have done a nice job both bringing their data up to date and extending their work. For those interested, click on the visual above and check out all of the relevant links contained within this post.
On this tough day here in Michigan … here is the visualization from the Guardian. Bracketing poor performance in the domestic market, there are some bright spots here in the company’s worldwide sales.
Information Aesthetics is now highlighting Subsidyscope — a project designed to track how various institutions receive federal monies. Of particular interest is their visualization of disbursements under the Troubled Asset Relief Program (TARP). Sponsored by the PEW Charitable Trust, the site also contains .csv files for most of the underlying data.
On a recent flight, I read Jeffrey Toobin’s New Yorker Article on Chief Justice Roberts entitled “No More Mr. Nice Guy”. The exchange quoted above is drawn from this article. While I believe it is appropriate to engage empirical data where available, the underlying discussion is not one exclusively subjectable to empirical inquiry. Rather, it is, at least in part, a question in need of a formal theoretic model. Justice Roberts and Mr. Katyal are implicitly discussing a “state of the world” not yet realized but which would be realized if the statute were not to exist. What would benefit the discussion is principled manner to adjudicate between these two inferences drawn above. Namely, it would be useful to fully evaluate what behavior would likely follow if the statute were not to exist.
There exist a variety of mathematical modeling techniques which could inject some much needed rigor into the above discussion. To my knowledge, such an applied model has yet to be offered. The Supreme Court’s decision in the matter is soon forthcoming. Given the nature of the exchange above, there is reason to believe that if Chief Justice Roberts prevails ….we will get our model as the “state of the world” discussed above will no longer be hypothetical….
Important thing worth noting … data.gov went online during our break …. From the front page “The purpose of Data.gov is to increase public access to high value, machine readable datasets generated by the Executive Branch of the Federal Government. Although the initial launch of Data.gov provides a limited portion of the rich variety of Federal datasets presently available, we invite you to actively participate in shaping the future of Data.gov by suggesting additional datasets and site enhancements to provide seamless access and use of your Federal data. Visit today with us, but come back often. With your help, Data.gov will continue to grow and change in the weeks, months, and years ahead.”