I-Corps: Using Artificial Social Intelligence for Legal Team Assistants

点击翻译按钮获取中文摘要

The broader impact/commercial potential of this I-Corps project is to substantially transform the legal system and processes by incorporating Artificial Intelligence (AI) into the legal process of discovering and analyzing information. This project provides the legal community with AI tools that will enable them to adapt to a fast-changing information landscape (i.e., by procuring, organizing and extracting actionable knowledge from large amounts of documents and data during the pre-trial procedure of discovery), and to leverage the most recent advances on human-machine teaming for an effective delivery of AI-assisted discovery to legal teams. The target customers are practitioners at law firms, corporations, government agencies, and academic researchers and who perform qualitative data analysis on large volumes of unstructured data. This technology potentially aids the case discovery process in the legal field that often involves large amounts of electronically stored information in preparation for litigation.This I-Corps project is based on advance machine learning based algorithms and social teaming algorithms used to improve the efficiency of qualitative data analysis and the effectiveness of data result delivery to legal teams. The project explores the use of artificial social intelligence-based algorithms that automate the analysis of large volumes of unstructured text data to gain insights to the patterns within the data more efficiently, with better individual and inter-coder reliability, and within significantly shorter processing time. The results of this analysis will be delivered to legal teams using computer-based agents that observe their surroundings, infer their teammates goals and assist the legal team by providing information at the appropriate level and time.This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.