Filtering of Brand-Related Microblogs Using Social-Smooth Multiview Embedding

摘要

In recent years, we have witnessed the boom of social media platforms, through which people have been generating a lot of social media data. This data touches almost every aspect of life and may have significant societal and marketing values for a variety of corporations and organizations. Thus, the development of effective techniques for gathering and analyzing social media content has attracted much research attention. As social media data tend to be heterogeneous, conversational, and fast evolving in content, a recent work reported a multifaceted approach to gather comprehensive brand-related data by crawling data using evolving keywords, key users, similar image content, and known locations. Although such approach has been found to be effective in gathering representative data, it also brings in a lot of noise. This paper aims to develop an accurate classifier to filter out noise by taking into account the multimedia content and social nature of brand-related data. In particular, we develop a microblog filtering method based on a discriminative social-aware multiview embedding. Besides the conventional content-based features, such as textual, low-level visual features, and high-level visual semantic features, that form the three key views of microblogs, we also incorporate the brand and social relations among the microblogs to learn a discriminative and social-aware embedding. With such a learned embedding, an off-the-shelf classifier, such as SVM, can then be trained and applied to microblog filtering. We verify the efficacy of our method on noise filtering in the brand data gathering task on the Brand-Social-Net dataset. Our approach is able to achieve significantly better filtering performance and improve the quality of brand data gathering.