Comparing Social Tags to Microblogs

As Internet usage and e-commerce grow, online social media serve as popular outlets for consumers to express sentiments about products. On Amazon, users can tag an album with a keyword, while tweets on Twitter represent a more natural conversation. The differing natures of these media make them difficult to compare. This project collects and analyzes social media data for newly released music albums and develops new methods of comparing a product's social tags to its micro logging data. It explores information retrieval and rank correlation measures as similarity measures, as well as term frequency-inverse document frequency (tf-idf) processing. We conclude that with sufficient Twitter activity about an album, social tags do represent the most frequent conversations occurring on Twitter. These results imply that managers can collect and analyze tags and use them as a proxy for most common consumer feedback from microblogging, which is more difficult to collect.