Topical Generalization for Presentation of User Profiles
This work addresses the problem of presenting user profiles for human readability, which is incremental as it builds on existing topical profiling methods for search and personalization.
The paper tackled the challenge of making fine-grained user profiles useful for human consumption by developing a topical generalization approach that groups topics and adds labels using the Wikipedia category graph. In a user study, a nested layout with this approach was preferred over a flat layout, but users overlooked lower-level topics, leading to a proposed third layout mode.
Fine-grained user profile generation approaches have made it increasingly feasible to display on a profile page in which topics a user has expertise or interest. Earlier work on topical user profiling has been directed at enhancing search and personalization functionality, but making such profiles useful for human consumption presents new challenges. With this work, we have taken a first step toward a semantic layout mode for topical user profiles. We have developed a topical generalization approach which finds coherent groups of topics and adds labels to them, based on their association with broader topics in the Wikipedia category graph. A nested layout mode, employing topical generalization, is compared with a simpler flat layout mode in our user study. The results indicate that users favor the nested structure over flat profiles, but tend to overlook the specific topics on the lower level. We propose a third layout mode to address this issue.