Semantic Annotation for Microblog Topics Using Wikipedia Temporal Information
نویسندگان
چکیده
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.
منابع مشابه
Wikipedia-based Topic Clustering for Microblogs
Microblogging has become a primary channel by which people not only share information, but also search for information. However, microblog search results are most often displayed by simple criteria such as creation time or author. A review of the literature suggests that clustering by topic may be useful, but short posts offer limited scope for clustering using lexical evidence alone. This pape...
متن کاملConcept Detection and Using Concept in adhoc of Microblog Search
We report our system and experiments in TREC 2012 microblog Ad-hoc task. Our goal is to return most relevant tweets to satisfy user’s information needs which are represented by short keyword queries. In additional to the last year’s temporal approach, we used Wikipedia pages to detect concepts of each query. And based on the concepts we detected, we did query expansion and concepts weighting se...
متن کاملThe Impact of Semantic Document Expansion on Cluster-Based Fusion for Microblog Search
Searching microblog posts, with their limited length and creative language usage, is challenging. We frame the microblog search problem as a data fusion problem. We examine the effectiveness of a recent cluster-based fusion method on the task of retrieving microblog posts. We find that in the optimal setting the contribution of the clustering information is very limited, which we hypothesize to...
متن کاملAdvertising Keyword Suggestion Using Relevance-Based Language Models from Wikipedia Rich Articles
When emerging technologies such as Search Engine Marketing (SEM) face tasks that require human level intelligence, it is inevitable to use the knowledge repositories to endow the machine with the breadth of knowledge available to humans. Keyword suggestion for search engine advertising is an important problem for sponsored search and SEM that requires a goldmine repository of knowledge. A recen...
متن کاملNovaSearch at TREC 2014 Microblog Track: Reranking with Wikipedia Page Views
This paper describes our participation in the TREC 2014 Microblog real-time search task. We investigate whether page views from Wikipedia can be used successfully to estimate relevant time periods for queries. To this end, we use a recently published temporal reranking method by Efron et al. [2], which uses kernel density estimation.
متن کامل