The aim of the study was to analyze freely generated self-presentations through the natural language processing technique of Latent Semantic Analysis (LSA). Four hundred fifty-one participants (F = 360; M = 143) recruited from LinkedIn (a professional social network) were randomly assigned to generate 10 words to describe themselves to either an employer (recruitment-condition) or a friend (friendship-condition). The words frequency-rate and their semantic representation were compared between conditions and to the natural language (Googles n-gram database). Self-presentations produced in the recruitment condition (vs. natural language) had significantly higher number of agentic words (e.g., problemsolver, responsible, able team-worker) and their contents were semantically closer to the concept of agency (i.e., competence, assertiveness, decisiveness) comparing to the friendship condition. Furthermore, the valence of the self-presentations words was higher (i.e., with a more positive meaning) in the recruitment condition. Altogether, these findings are consistent with the literature on the "Big Two," self-presentation, and impression management.