Mining and predicting temporal patterns in the quality evolution of Wikipedia articles

Haifeng Zhang, Yuqing Ren, Robert E. Kraut

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Online open collaboration systems like Wikipedia are complex adaptive systems within which large numbers of individual agents and artifacts interact and co-evolve over time. A key issue in these systems is the quality of the co-created artifacts and the processes through which high-quality artifacts are produced. In this paper, we took a dynamic approach to uncover common patterns in the temporal evolution of 6,057 Wikipedia articles in the domains of roads, films, and battles. Using Dynamic Time Warping, an advanced time-series clustering method, we identified three distinctive growth patterns, namely, stalled, plateaued, and sustained. Multinomial logistic regressions to predict these different clusters suggest that the path that an article follows is determined by both its inherent attributes, such as topic importance, and the contribution and coordination of editors who collaborated on the article. Our results also suggest that different factors matter at different stages of an article's life cycle.

Original languageEnglish (US)
Title of host publicationProceedings of the 53rd Annual Hawaii International Conference on System Sciences, HICSS 2020
EditorsTung X. Bui
PublisherIEEE Computer Society
Pages3971-3980
Number of pages10
ISBN (Electronic)9780998133133
StatePublished - 2020
Event53rd Annual Hawaii International Conference on System Sciences, HICSS 2020 - Maui, United States
Duration: Jan 7 2020Jan 10 2020

Publication series

NameProceedings of the Annual Hawaii International Conference on System Sciences
Volume2020-January
ISSN (Print)1530-1605

Conference

Conference53rd Annual Hawaii International Conference on System Sciences, HICSS 2020
Country/TerritoryUnited States
CityMaui
Period1/7/201/10/20

Bibliographical note

Publisher Copyright:
© 2020 IEEE Computer Society. All rights reserved.

Fingerprint

Dive into the research topics of 'Mining and predicting temporal patterns in the quality evolution of Wikipedia articles'. Together they form a unique fingerprint.

Cite this