Analyzing customer sentiments in microblogs – A topic-model-based approach for Twitter datasets
Business Intelligence and Knowledge Management
In the Social Commerce customers evolve to an important information source for companies. The customers use communication platforms of the Web 2.0, for example Twitter, in order to express their opinions about products or discuss their experiences with them. These opinions can be very important for the development of products or the product range of a company. Our approach enables a company viewing opinions about its products which are published using the microblogging service Twitter. A first step in our research progress is detecting topics in a specific context. In a further step the entries corresponding to these topics has to be analyzed for opinions. For topic detection we use topic modeling with the Latent Dirichlet Allocation. In our paper we found event-based topics in the context of Sony’s 3D TV sets. In future work we are able to implement Opinion Mining algorithms to determine sentiments in the entries corresponding to the detected topics.
Sommer, Stefan; Schieber, Andreas; Hilbert, Andreas; and Heinrich, Kai, "Analyzing customer sentiments in microblogs – A topic-model-based approach for Twitter datasets" (2011). AMCIS 2011 Proceedings - All Submissions. 227.