Semantic Annotation for Microblog Topics Using Wikipedia Temporal Information
T. Tran, N. Tran, A. Teka Hadgu, и R. Jäschke. Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing (EMNLP), Association for Computational Linguistics, (сентября 2015)
Аннотация
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.
%0 Conference Paper
%1 tran2015semantic
%A Tran, Tuan
%A Tran, Nam-Khanh
%A Teka Hadgu, Asmelash
%A Jäschke, Robert
%B Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing (EMNLP)
%D 2015
%I Association for Computational Linguistics
%K alexandria annotation forgetit gutearbeit l3s l3s_twitter microblog myown qualimaster semantic wikipedia
%T Semantic Annotation for Microblog Topics Using Wikipedia Temporal Information
%X 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.
@inproceedings{tran2015semantic,
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.},
added-at = {2015-07-31T16:16:58.000+0200},
author = {Tran, Tuan and Tran, Nam-Khanh and Teka Hadgu, Asmelash and Jäschke, Robert},
biburl = {https://www.bibsonomy.org/bibtex/29d4cd9070922e1eb43bcab1da4a9d840/antoine-tran},
booktitle = {Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing (EMNLP)},
interhash = {4156275c801376fa64dfdb69a4ce60c4},
intrahash = {9d4cd9070922e1eb43bcab1da4a9d840},
keywords = {alexandria annotation forgetit gutearbeit l3s l3s_twitter microblog myown qualimaster semantic wikipedia},
month = sep,
publisher = {Association for Computational Linguistics},
timestamp = {2017-01-14T17:55:08.000+0100},
title = {Semantic Annotation for Microblog Topics Using Wikipedia Temporal Information},
year = 2015
}