Personalized Microblog Search on Twitter:
Institution: | Delft University of Technology |
---|---|
Department: | |
Year: | 2014 |
Keywords: | personalized search; microblog search; user modeling; information retrieval |
Record ID: | 1253170 |
Full text PDF: | http://resolver.tudelft.nl/uuid:d19a1d28-e3eb-420a-a872-5a40baadcc09 |
This thesis describes our approach to microblog search personalization. The approach uti-lizes implicit information about the user’s interests to personalize original search results. We first present how do we model users’ preferences on Twitter. Subsequently, we investi-gate different ways to represent search results so that they can be compared with users’ preferences. In addition, we provide a set of personalized strategies and evaluate them in two experiments. Furthermore, we compare the performance of our personalized strategies and further analyze their impacts on the retrieval effectiveness. Our research suggests that our personalized search approach can enhance the retrieval performance on Twitter.