A Framework for Collecting and Managing Entity Identity Information from Social Media

摘要

An entity in general may be defined as an object that has a distinct, independent and self-contained existence.rnAn entity could be a person, place, product, real-life event, or anything that has an individual identity. Thernidentity of an entity is a set of attributes that distinctly characterizes it and differentiates it from all otherrnentities. With the popularity of social media, there has been voluminous growth in the digital footprints ofrndifferent types of entities in the Internet. The references to different types of entities in social media have thernpotential to provide extremely valuable information to researchers and organizations, which could be minedrnand analyzed for making major decisions. There are tremendous applications in the areas of real-life eventrnanalysis, opinion mining, reference tracking, online advertising, recommendation engines, cyber security,rnfraud detection, enterprise data integration, among others. Thus, there is a need of a generic framework thatrncan collect different entity references, extract identity information of the entities from them and maintain therninformation persistently for resolving new references of entities. The presented research establishes thernpreliminary design of such a framework from the perspective of Entity Identity Information Managementrn(EIIM) in the domain of social media. The paper introduces the problem of EIIM in social media, discusses thernprevalent challenges and proposes the design of a framework capable of managing persistent identityrninformation of pre-specified set of entities. We further explore the applications of the research and concludernwith the future plan of action for implementing an EIIM system in the realm of social media.