Difference between revisions of "Semantic Annotation for Microblog Topics Using Wikipedia Temporal Information"
(Adding wikilinks) |
(+ Infobox work) |
||
| Line 1: | Line 1: | ||
| + | {{Infobox work | ||
| + | | title = Semantic Annotation for Microblog Topics Using Wikipedia Temporal Information | ||
| + | | date = 2015 | ||
| + | | authors = [[Tuan Tran]]<br />[[Nam Khanh Tran]]<br />[[Asmelash Teka Hadgu]] | ||
| + | | doi = 10.18653/v1/D15-1010 | ||
| + | | link = https://www.cse.iitb.ac.in/~pb/papers/coling12-YouCat.pdf | ||
| + | | plink = http://arxiv.org/pdf/1701.03939.pdf | ||
| + | }} | ||
'''Semantic Annotation for Microblog Topics Using Wikipedia Temporal Information''' - scientific work related to [[Wikipedia quality]] published in 2015, written by [[Tuan Tran]], [[Nam Khanh Tran]] and [[Asmelash Teka Hadgu]]. | '''Semantic Annotation for Microblog Topics Using Wikipedia Temporal Information''' - scientific work related to [[Wikipedia quality]] published in 2015, written by [[Tuan Tran]], [[Nam Khanh Tran]] and [[Asmelash Teka Hadgu]]. | ||
== Overview == | == Overview == | ||
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, authors tackle the problem of mapping trending Twitter topics to entities from [[Wikipedia]]. Authors 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, authors have improved the annotation performance by 17-28%, as compared to the competitive 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, authors tackle the problem of mapping trending Twitter topics to entities from [[Wikipedia]]. Authors 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, authors have improved the annotation performance by 17-28%, as compared to the competitive baselines. | ||
Revision as of 11:58, 15 September 2019
Authors | Tuan Tran Nam Khanh Tran Asmelash Teka Hadgu |
|---|---|
Publication date | 2015 |
DOI | 10.18653/v1/D15-1010 |
Links | Original Preprint |
Semantic Annotation for Microblog Topics Using Wikipedia Temporal Information - scientific work related to Wikipedia quality published in 2015, written by Tuan Tran, Nam Khanh Tran and Asmelash Teka Hadgu.
Overview
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, authors tackle the problem of mapping trending Twitter topics to entities from Wikipedia. Authors 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, authors have improved the annotation performance by 17-28%, as compared to the competitive baselines.
