Brand Data Gathering From Live Social Media Streams

Abstract

Social media streams, such as Twitter, Facebook, and Sina Weibo, have become essential real-time information resources with a wide range of users and applications. The rapidly increasing amount of live information in social media streams has important societal and marketing values for large corporations and government organizations. There is a strong need for effective techniques for data gathering and content analysis. This problem is particularly challenging due to the short and conversational nature of posts, the huge data volume, and the increasing heterogeneous multimedia content in social media streams. Moreover, as the focus of "conversation" often shifts quickly in social media space, the traditional keywords based approach to gather data with respect to a target brand is grossly inadequate. To address these problems, we propose a multi-faceted brand tracking method that gathers relevant data based on not just evolving keywords, but also social factors (users, relations and locations) as well as visual contents as increasing number of social media posts are in multimedia form. For evaluation, we set up a large scale microblog dataset (Brand-Social-Net) on brand/product information, containing 3 million microblogs with over 1.2 million images for 100 famous brands. Experiments on this dataset have demonstrated that the proposed framework is able to gather a more complete set of relevant brand-related data from live social media streams. We have released this dataset to promote social media research.

[Invited Paper] A Review of Web Image Mining

“…Some geotagged ramen photos collected in several hours are shown in Figure 7. Gao et al 43) proposed a method to mine brand product photos from Weibo which employs supervised image recognition in the same ways as 145). They integrated and used visual features and social factors (users, relations, and locations) as well as textual features.…”

Decomposed human localization from social photo album

“…And the clothing information was utilized to identify the same person [22], EasyAlbum [23] enables the feature-oriented image browsing functionality by putting photos with similar scenes or similar faces together. A hypergraph-based approach is proposed to simultaneously utilize visual information and tags for image relevance learning [24,25]. However, we step into a more complicated scenario, where poses of persons are indirect retrieval keywords.…”

Deep Hierarchical Representation from Classifying Logo-405

“…Logos can be composed of a glyph, a textual message, an icon, or an image, depicted in various colors and styles. Detection and recognition of logos has always been important in a wide range of applications, such as product or brand identification, copyright infringement detection, contextual advertise placement, vehicle logo for intelligent traffic-control system [1], and brand-related statistics from social media streams [2]. At present, with the rapid development of multimedia information technology, the amount of logo data on the Internet continues to grow.…”