An e-mail address is a source of communication for major social networking sites. In general, e-mail addresses hold identity in the form a surname as a substring in it. Identities such as names are far from random and can exhibit community distributions over populations. However, these identities reflect cultural, ethnic, and genetic structures generated among populations. Hence, identity establishment in e-mail address mining can be seen as a categorization of e-mail address-based community structure in names data set. It involves community modeling in names, categorization of an e-mail addresses, and identity privacy preservation. This chapter presents a survey of text mining and privacy preserving techniques followed by research challenges and strategies in name analysis. The research challenges are: (1) e-mail address categorization based on community structure of identities, (2) correlation of surnames and forenames within and across communities, and (3) privacy preserving of identities in communities.