Semantic Annotation for Microblog Topics Using Wikipedia Temporal Information

TL;DR

This paper presents a novel approach for semantic annotation of Twitter trending topics by leveraging Wikipedia's temporal data, significantly improving annotation accuracy during burst periods.

Contribution

The work introduces a new model that incorporates Wikipedia's temporal information to enhance microblog topic annotation, addressing a largely unexplored research area.

Findings

Improved annotation performance by 17-28% using temporal data.

Utilized Wikipedia edit history and page views for better entity mapping.

Enhanced understanding of social events through better semantic annotation.

Abstract

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.