文章基本信息

标题：myDIG: Personalized Illicit Domain-Specific Knowledge Discovery with No Programming
本地全文：下载
作者：Mayank Kejriwal ; Mayank Kejriwal ; Pedro Szekely 等
期刊名称：Future Internet
电子版ISSN：1999-5903
出版年度：2019
卷号：11
期号：3
页码：59
DOI：10.3390/fi11030059
出版社：MDPI Publishing
摘要：With advances in machine learning, knowledge discovery systems have become very complicated to set up, requiring extensive tuning and programming effort. Democratizing such technology so that non-technical domain experts can avail themselves of these advances in an interactive and personalized way is an important problem. We describe myDIG, a highly modular, open source pipeline-construction system that is specifically geared towards investigative users (e.g., law enforcement) with no programming abilities. The myDIG system allows users both to build a knowledge graph of entities, relationships, and attributes for illicit domains from a raw HTML corpus and also to set up a personalized search interface for analyzing the structured knowledge. We use qualitative and quantitative data from five case studies involving investigative experts from illicit domains such as securities fraud and illegal firearms sales to illustrate the potential of myDIG.
关键词：knowledge discovery; domain specific; no programming; knowledge graphs; information extraction; investigative domains; search; personalized analytics knowledge discovery ; domain specific ; no programming ; knowledge graphs ; information extraction ; investigative domains ; search ; personalized analytics