The Big Data Challenge Within the Legal Community

Big Data, it seems, is everywhere. The capacity and speed delivered by new technology systems allows incomprehensibly large sets of data to be analysed by computers, revealing patterns, trends, and associations that can then be used to analyse and predict with greater certainty. This is very useful in the practice of law which is characterised by an enormous and ever-growing amount of data. Here Robin Chesterman, Head of Product at Justis, delves deep into the challenges the legal sphere currently faces with big data implementation.

For lawyers deploying the systems which support new cases, new legislation and new judgments, it has meant taking advantage of the digitisation of existing data and a vast amount of new data capture. But there is a catch. Although these gargantuan data sets are now more readily available, they have not yet become easier for lawyers to access, or to manage. In fact, innovation in how lawyers try to use all of that data to best advantage has been surprisingly slow. This Big Data problem is an increasing challenge for lawyers everywhere.

At present, Big Data tools for the legal profession are focused primarily on helping law firms to enhance their internal business functions and processes, such as time management and billing, or for predictive analytics in a range of internal legal applications. Document and contract management systems proliferate. They are expanding rapidly as a host of companies compete to develop platforms, many of them with AI capacity, that organise, summarise and analyse data so that it delivers genuine value in saving time when producing documents, and increasingly, as a flexible predictive tool.

By contrast, developing tools for the research and case preparation elements of their advisory work have seen notably much less innovation for lawyers. This leaves legal researchers often lacking easy access to the data that they need because they do not have the appropriate tools to undertake their research effectively.

Conventional legal data-driven research companies hold databases which contain enormous volumes of case information stretching back over centuries and across multiple jurisdictions. As the common starting point for legal researchers, they operate primarily as search engines with relatively few advanced analytical tools available for use. Meanwhile many legal researchers do not necessarily want to analyse historic legal data, but rather brand new incoming data.

These traditional platforms, which have become the standard default for many of those engaged in legal research, do not offer the right sort of technology to support the enormous volumes of data which they hold. Instead, platforms are needed to provide full comprehensive technological support which will allow researchers and practitioners to review the enormous quantity of case law that is being created and uploaded every year.

To address this shortcoming, JustisOne – the legal research platform operated by Justis – is now attempting to make the wealth of judgments (both reported and unreported) accessible and useful to practitioners. By making data analytics an automated part of the research process, JustisOne enables practitioners to focus more on the case itself rather than having to comb through judgments to find supporting case law. To achieve this, an assortment of sophisticated technologies are being deployed by Justis which are not currently used in combination by any other provider.

For researchers, the ‘Key Passages’ feature provides a simple, but effective way of viewing key aspects of any published judgment – highlighting the paragraphs that are most cited in other cases, and providing a link to the specific parts of those cases that discuss it. Beyond this cross-referencing of cases, the Justis team of legally qualified editors can also analyse the treatment given to each judgment, allowing practitioners to see at a glance the status of the law with reference to a multiplicity of judgments.

In further support, there is a unique data visualisation system that allows a single judgment to be viewed in the context of all other cases where it has been referenced. A practitioner is therefore able to instantly see which other cases have discussed the current case, as well as the relevance of those other cases by date and influence on each other.

Not every innovation needs to be complex. Even simple innovations can have an impact on the efficiency of legal research. Additional features such as side-by-side judgment analysis, indexed content from other platforms that links directly to the source, and a legal taxonomy which holds more than 1.5m search terms help to streamline the research process, simplify the work of practitioners, and save time.

As Big Data is applied across multiple aspects and categories of work done by law firms internally and on behalf of their clients, legal research has been slow to keep pace. But it is now catching up fast.