Whose profile is this?

Whose profile is this?

Problem being addressed

Tumblr is a leading content provider and social media​,​ which means great opportunities for advertisers to promote their products through sponsored posts; however​,​ it is a challenging task to target specific demographic groups for ads​,​ since Tumblr does not require user information like gender and ages during their registration.

Solution

To promote ad targeting, it is essential to predict user’s demography using rich content such as posts, images and social connections. The suggested approach combines graph based and deep learning models for age and gender predictions, which take into account user activities and content features.

Advantages of this solution

Experimental results on real Tumblr daily dataset, with hundreds of millions of active users and billions of following relations, demonstrate that the suggested approaches significantly outperform the baseline model, by improving the accuracy relatively by 81% for age, and accuracy by 5% for gender.

Solution originally applied in these industries

advertising

Advertising Industry

Possible New Application of the Work

data:image/png;base64,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

Media

Predicting the characteristics of the user profiles in social media allows its better analysis and detection of potential trends and identifying aggressors or biased groups.

data:image/png;base64,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

Other Industry

Security industry: better profile prediction will allow to detect and identify abusers and stalkers, which can be hard to trace considering the anonymity that internet provides. It can also prevent certain types of crime, like terrorism and mass shooting, by predictive analytics of people's profiles and better profile identification.

Source URL: #############check-icon


search-iconBrowse all blitzcards