TREC Legal Track Research Articles

Performance Comparison and Optimization of Text Document Classification using k-NN and Naïve Bayes Classification Techniques

In the current era, information is available in several different formats, such as text, image, video, audio and others. Corpus is a collection of documents in a large volume. By using Information Retrieval (IR), it is possible to obtain an unstructured information and automatic summary, classification and clustering. This research is to focus on data classification using two out of the six approaches of data classification, which is k-NN (k-Nearest Neighbors) and Naïve Bayes. The text documents used is in XML format. The Corpus used in this research is downloaded from TREC Legal Track with a total of more than three thousand text documents and over twenty types of classifications. Out of the twenty types of classifications, six are chosen with the most number of text documents. The data is processed using RapidMiner software and the result shows that the optimum value for k in k-NN occurs at k=13. Using this value for k, the accruacy in average reached 55.17 percent, which is better than using Naïve Bayes which is 39.01 percent.

Toward a new jurisprudence of information retrieval: What constitutes a “reasonable” search for digital evidence when using keywords?

Conference paper by Jason R. Baron, Director of Litigation at the U.S. National Archives and Records Administration, an Adjunct Professor, School of Information Studies, University of Maryland, and serves as Editor-in-Chief of The Sedona Conference® Best Practices Commentary on the Use of Search and Information Retrieval, and a founding coordinator of the TREC Legal Track.

Approximate Recall Confidence Intervals

Recall, the proportion of relevant documents retrieved, is an important measure of effectiveness in information retrieval, particularly in the legal, patent, and medical domains. Where document sets are too large for exhaustive relevance assessment, recall can be estimated by assessing a random sample of documents, but an indication of the reliability of this estimate is also required. In this article, we examine several methods for estimating two-tailed recall confidence intervals. We find that the normal approximation in current use provides poor coverage in many circumstances, even when adjusted to correct its inappropriate symmetry. Analytic and Bayesian methods based on the ratio of binomials are generally more accurate but are inaccurate on small populations. The method we recommend derives beta-binomial posteriors on retrieved and unretrieved yield, with fixed hyperparameters, and a Monte Carlo estimate of the posterior distribution of recall. We demonstrate that this method gives mean coverage at or near the nominal level, across several scenarios, while being balanced and stable. We offer advice on sampling design, including the allocation of assessments to the retrieved and unretrieved segments, and compare the proposed beta-binomial with the officially reported normal intervals for recent TREC Legal Track iterations.

Factors affecting relevance judgment: a report from TREC Legal track

PurposeThis study intends to identify factors that affect relevance judgment of retrieved information as part of the 2007 TREC Legal track interactive task.Design/methodology/approachData were gathered and analyzed from the participants of the 2007 TREC Legal track interactive task using a questionnaire which includes not only a list of 80 relevance factors identified in prior research, but also a space for expressing their thoughts on relevance judgment in the process.FindingsThis study finds that topicality remains a primary criterion, out of various options, for determining relevance, while specificity of the search request, task, or retrieved results also helps greatly in relevance judgment.Research limitations/implicationsRelevance research should focus on the topicality and specificity of what is being evaluated as well as conducted in real environments.Practical implicationsIf multiple relevance factors are presented to assessors, the total number in a list should be below ten to take account of the limited processing capacity of human beings' short‐term memory. Otherwise, the assessors might either completely ignore or inadequately consider some of the relevance factors when making judgment decisions.Originality/valueThis study presents a method for reducing the artificiality of relevance research design, an apparent limitation in many related studies. Specifically, relevance judgment was made in this research as part of the 2007 TREC Legal track interactive task rather than a study devised for the sake of it. The assessors also served as searchers so that their searching experience would facilitate their subsequent relevance judgments.