About this Research Topic
Over the past decade, the exponential growth of electronic text data in the legal industry has created a significant business challenge. Legal professionals often are overwhelmed by the electronic data in cases For example, typical antitrust investigation cases generally involve reviewing and producing terabytes of text data. This voluminous text data must be processed and analyzed to derive new insights, better judgments, and effective strategies in legal cases. Artificial intelligence (AI) technologies, in particular machine learning and text classification, have been increasingly embraced by the legal industry to efficiently review a large volume of complex legal data, to deliver legal services at reasonable costs, and satisfactory speed. Today, the global eDiscovery market was estimated to be greater than $11 billion in 2019. It is expected to exceed $20 billion by 2024. Document review is the most expansive part of an EDiscovery process.
Legal document review requires significant time and resources to meet production schedules established by the legal process. The costs of legal document review continue to escalate as the volumes of business data continue to grow. For more than ten years, attorneys have been using machine learning techniques like text classification to more efficiently cull massive volumes of data to identify relevant information. Text classification is applied to automatically classify documents into attorney-defined categories. This classification process is also used by attorneys for the identification of interesting documents in internal investigations or litigations and for the identification and protection of attorney-client privilege and confidential information. The applications of machine learning in legal document review have placed the legal services industry at a particularly exciting combination of challenges and opportunities. With both the challenges and opportunities, we have identified a gap between the legal industry and academics working with machine learning technologies. This Research Topic will bridge that gap, to further machine learning and text classification research applied to legal document review, and to provide an open dialogue about how these technologies could be leveraged to assist legal practitioners.
This Research Topic will accept broad applications of text classification and document clustering technologies to legal industry challenges. The following topics, but not limited to, are welcomed:
• Legal Text Classification
• Legal Document Clustering
• Explainable Legal Text Classification
• Responsible Text Classification
• Active Learning in Legal Text Classification
• Legal Text Classification using Deep Learning Technologies
• Case Studies of Legal Text Classification and Document Clustering
Topic editors Jianping Zhang and Haozhen Zhao are employed by Ankura Consulting Group, LLLC. Topic editor Jianping Zhang also holds shares in the company, Ankura Consulting Group, LLLC. All other Topic Editors declare no competing interests with regards to the Research Topic subject.
Legal document review requires significant time and resources to meet production schedules established by the legal process. The costs of legal document review continue to escalate as the volumes of business data continue to grow. For more than ten years, attorneys have been using machine learning techniques like text classification to more efficiently cull massive volumes of data to identify relevant information. Text classification is applied to automatically classify documents into attorney-defined categories. This classification process is also used by attorneys for the identification of interesting documents in internal investigations or litigations and for the identification and protection of attorney-client privilege and confidential information. The applications of machine learning in legal document review have placed the legal services industry at a particularly exciting combination of challenges and opportunities. With both the challenges and opportunities, we have identified a gap between the legal industry and academics working with machine learning technologies. This Research Topic will bridge that gap, to further machine learning and text classification research applied to legal document review, and to provide an open dialogue about how these technologies could be leveraged to assist legal practitioners.
This Research Topic will accept broad applications of text classification and document clustering technologies to legal industry challenges. The following topics, but not limited to, are welcomed:
• Legal Text Classification
• Legal Document Clustering
• Explainable Legal Text Classification
• Responsible Text Classification
• Active Learning in Legal Text Classification
• Legal Text Classification using Deep Learning Technologies
• Case Studies of Legal Text Classification and Document Clustering
Topic editors Jianping Zhang and Haozhen Zhao are employed by Ankura Consulting Group, LLLC. Topic editor Jianping Zhang also holds shares in the company, Ankura Consulting Group, LLLC. All other Topic Editors declare no competing interests with regards to the Research Topic subject.
Keywords: Machine learning, Legal document review, Electronic discovery, Text Classification, Document clustering
Important Note: All contributions to this Research Topic must be within the scope of the section and journal to which they are submitted, as defined in their mission statements. Frontiers reserves the right to guide an out-of-scope manuscript to a more suitable section or journal at any stage of peer review.
