Semantic Annotation for Microblog Topics Using Wikipedia Temporal Information
This work addresses the need for better semantic analysis of microblog trends, which is important for researchers and analysts studying social events, though it is incremental as it builds on existing text-based methods.
The paper tackled the problem of mapping trending Twitter topics to Wikipedia entities by proposing a model that uses temporal correlation from Wikipedia edit history and page view logs, improving annotation performance by 17-28% compared to baselines.
Trending topics in microblogs such as Twitter are valuable resources to understand social aspects of real-world events. To enable deep analyses of such trends, semantic annotation is an effective approach; yet the problem of annotating microblog trending topics is largely unexplored by the research community. In this work, we tackle the problem of mapping trending Twitter topics to entities from Wikipedia. We propose a novel model that complements traditional text-based approaches by rewarding entities that exhibit a high temporal correlation with topics during their burst time period. By exploiting temporal information from the Wikipedia edit history and page view logs, we have improved the annotation performance by 17-28\%, as compared to the competitive baselines.