Beyond Classification: Latent User Interests Profiling from Visual Contents Analysis

Abstract

User preference profiling is an important task in modern online social networks (OSN). With the proliferation of image-centric social platforms, such as Pinterest, visual contents have become one of the most informative data streams for understanding user preferences. Traditional approaches usually treat visual content analysis as a general classification problem where one or more labels are assigned to each image. Although such an approach simplifies the process of image analysis, it misses the rich context and visual cues that play an important role in people's perception of images. In this paper, we explore the possibilities of learning a user's latent visual preferences directly from image contents. We propose a distance metric learning method based on Deep Convolutional Neural Networks (CNN) to directly extract similarity information from visual contents and use the derived distance metric to mine individual users' fine-grained visual preferences. Through our preliminary experiments using data from 5,790 Pinterest users, we show that even for the images within the same category, each user possesses distinct and individually-identifiable visual preferences that are consistent over their lifetime. Our results underscore the untapped potential of finer-grained visual preference profiling in understanding users' preferences.

2015 IEEE 15th International Conference on Data Mining Workshops

References in corpus (4)

• Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
• Distributed Representations of Sentences and Documents
• Caffe: Convolutional Architecture for Fast Feature Embedding
• A Picture Tells a Thousand Words -- About You! User Interest Profiling from User Generated Visual Content

Cited by in corpus (5)

• Yum-me: A Personalized Nutrient-based Meal Recommender System
• Preferences Prediction using a Gallery of Mobile Device based on Scene Recognition and Object Detection
• A visual approach for age and gender identification on Twitter
• Connection Discovery using Shared Images by Gaussian Relational Topic Model
• DeepVisInterests: CNN-Ontology Prediction of Users Interests from Social Images