Image tagging and search: a gender oriented study

Adrian Popescu (1) , Gregory Grefenstette (2)

1 INFO - Département informatique
2 Exalead

Social computing sites constitute a valuable source of usergenerated content for user modeling. Whereas user generated content and the mining of such content are well studied, little attention has been given in the literature to modeling the relationship between users' personal information and content. Here we analyze the relation of user gender to the choice of tags to describe a photo. A large user sample is examined to produce gender-related tagging vocabularies and tag representations. 1000 salient tags male and female representations are compared and results indicate that there are important differences between gender based term choices in a large majority of cases. To test the influence of gender on retrieval, we built a gender sensitive image search prototype and tested it, using a survey. Results show that around two thirds of participants tend to prefer image search results obtained using tag representations of their own gender and that a third of participants have a clear preference for their own genders results.

Mots clés: Gender; Image search; Social network; Flickr

Adrian Popescu, Gregory Grefenstette. Image tagging and search: a gender oriented study. 2d AMC Workshop on Social Media, Oct 2010, Florence, Italy. ⟨hal-00725609⟩