VizByWiki: Mining Data Visualizations from the Web to Enrich News Articles
作者： Allen Yilun Lin , Joshua Ford , Eytan Adar , Brent Hecht
关键词:
摘要: Data visualizations in news articles (e.g., maps, line graphs, bar charts) greatly enrich the content of and result well-established improvements to reader comprehension. However, existing systems that generate data visualiza-tions either require substantial manual effort or are limited very specific types visualizations, thereby re-stricting number can be enhanced. To address this issue, we define a new problem: given ar-ticle, retrieve relevant already exist on web. We show problem is tractable through system, VizByWiki, mines contextually from Wikimedia Commons, central file reposi-tory for Wikipedia. Using novel ground truth dataset, VizByWiki successfully augment as many 48% popular online with visualizations. also demonstrate automatically rank according their usefulness reasonable accuracy (nDCG@5 0.82). facilitate further advances our "news visualization retrieval problem", release dataset make system its source code publicly available.
sci-hub.se 参考文章(36)
Arvind Satyanarayan, Jeffrey Heer, Lyra: An Interactive Visualization Design Environment eurographics. ,vol. 33, pp. 351- 360 ,(2014) , 10.1111/CGF.12391
Shuo Chang, Peng Dai, Jilin Chen, Ed H. Chi, Got Many Labels?: Deriving Topic Labels from Multiple Sources for Social Media Posts using Crowdsourcing and Ensemble Learning the web conference. pp. 397- 406 ,(2015) , 10.1145/2740908.2745401
Kanit Wongsuphasawat, Dominik Moritz, Anushka Anand, Jock Mackinlay, Bill Howe, Jeffrey Heer, Voyager: Exploratory Analysis via Faceted Browsing of Visualization Recommendations IEEE Transactions on Visualization and Computer Graphics. ,vol. 22, pp. 649- 658 ,(2016) , 10.1109/TVCG.2015.2467191
Thanapon Noraset, Chandra Bhagavatula, Doug Downey, WebSAIL wikifier at ERD 2014 international acm sigir conference on research and development in information retrieval. pp. 119- 124 ,(2014) , 10.1145/2633211.2639489
Tong Gao, Jessica R. Hullman, Eytan Adar, Brent Hecht, Nicholas Diakopoulos, NewsViews: an automated pipeline for creating custom geovisualizations for news human factors in computing systems. pp. 3005- 3014 ,(2014) , 10.1145/2556288.2557228
Zechao Li, Meng Wang, Jing Liu, Changsheng Xu, Hanqing Lu, News contextualization with geographic and visual information Proceedings of the 19th ACM international conference on Multimedia - MM '11. pp. 133- 142 ,(2011) , 10.1145/2072298.2072317
Diogo Delgado, Joao Magalhaes, Nuno Correia, Assisted news reading with automated illustration Proceedings of the international conference on Multimedia - MM '10. pp. 1647- 1650 ,(2010) , 10.1145/1873951.1874311
Thorsten Joachims, Optimizing search engines using clickthrough data Proceedings of the eighth ACM SIGKDD international conference on Knowledge discovery and data mining - KDD '02. pp. 133- 142 ,(2002) , 10.1145/775047.775067
Manolis Savva, Nicholas Kong, Arti Chhajta, Li Fei-Fei, Maneesh Agrawala, Jeffrey Heer, ReVision Proceedings of the 24th annual ACM symposium on User interface software and technology - UIST '11. pp. 393- 402 ,(2011) , 10.1145/2047196.2047247
Ali Sharif Razavian, Hossein Azizpour, Josephine Sullivan, Stefan Carlsson, CNN Features Off-the-Shelf: An Astounding Baseline for Recognition computer vision and pattern recognition. pp. 512- 519 ,(2014) , 10.1109/CVPRW.2014.131