Mining potential domain expertise in Pinterest Conference Paper uri icon

abstract

  • This paper describes a first investigation of potential domain expertise in Pinterest. We introduce measures for characterizing the volume and coherence of Pinterest users' pinning activity in a given category, their perceived and declared category-specific expertise and the response from the social network. We use such signals in the context of a supervised ML framework and report encouraging preliminary results on the task of mining potential experts for 4 popular content categories.

author list (cited authors)

  • Popescu, A. M., Kamath, K. Y., & Caverlee, J.

editor list (cited editors)

  • Berkovsky, S., Herder, E., Lops, P., & Santos, O. C.

publication date

  • January 2013