Predicting Low-Quality Wikipedia Articles Using User’s Judgements

  • Ning Zhang
  • Lingyun Ruan
  • Luo Si
Part of the Computational Social Sciences book series (CSS)


Wikipedia has become the most popular on-line encyclopedia. Millions of users rely on it to obtain desired knowledge and thus it becomes important and practical to model the quality of Wikipedia articles and to have inferior contents which bother readers or even mislead readers to be predicted. While identifying low-quality articles with manual efforts is a possible solution, it costs too much manpower and is too time-consuming. In this paper, we utilize article ratings from Wikipedia users for the first time to assess article quality. We define “low-quality” based on those ratings and design automatic methods to identify potential low-quality articles. More specifically, we formulate the problem as a set of binary classification problems and label articles according to whether they are “low-quality”. We compare two baseline algorithms and Logistic Regression algorithm, and the results indicate that it is promising to design effective and efficient automatic solutions for the task. We believe that our work is important for ensuring the quality of Wikipedia, as well as other knowledge markets.


WikipediaArticle qualityUser ratingPrediction 


  1. Adler, B., de Alfaro, L., & Pye, I. (2010). Detecting Wikipedia vandalism using WikiTrust. Notebook papers of CLEF, pp. 22–23.Google Scholar
  2. Adler, B. T., de Alfaro, L., Mola-Velasco, S. M., Rosso, P., & West, A. G. (2011). Wikipedia vandalism detection: Combining natural language, metadata, and reputation features. In Computational linguistics and intelligent text processing, pp. 277–288. (Springer).Google Scholar
  3. Anderka, M., Stein, B., & Lipka, N. (2012). Predicting quality flaws in user-generated content: The case of Wikipedia. Proceedings of the 35th international ACM SIGIR conference on research and development in information retrieval, pp. 981–990. (ACM).Google Scholar
  4. Blumenstock, J. E. (2008). Size matters: Word count as a measure of quality on Wikipedia. Proceedings of the 17th international conference on World Wide Web, pp. 1095–1096. (ACM).Google Scholar
  5. Hosmer, D. W. and Lemeshow, S. (2004). Applied logistic regression (Vol. 354). New York: Wiley.Google Scholar
  6. Hu, M., Lim, E.-P., Sun, A., Lauw, H. W., & Vuong, B.-Q. (2007). Measuring article quality in Wikipedia: Models and evaluation. Proceedings of the sixteenth ACM conference on information and knowledge management, pp. 243–252. (ACM).Google Scholar
  7. Potthast, M., Stein, B., & Gerling, R. (2008). Automatic vandalism detection in Wikipedia. InAdvances in information retrieval, pp. 663–668. (Springer).Google Scholar
  8. Smets, K., Goethals, B., & Verdonk, B. (2008). Automatic vandalism detection in Wikipedia: Towards a machine learning approach. AAAI workshop on Wikipedia and artificial intelligence: An Evolving Synergy, pp. 43–48.Google Scholar
  9. Stvilia, B., Twidale, M. B., Smith, L. C., & Gasser, L. (2005). Assessing information quality of a community-based encyclopedia. Proceedings of the international conference on information quality, pp. 442–454.Google Scholar
  10. Wilkinson, D. M., & Huberman, B. A. (2007). Cooperation and quality in Wikipedia. Proceedings of the 2007 international symposium on Wikis, pp. 157–164. (ACM).Google Scholar

Copyright information

© Springer International Publishing Switzerland 2015

Authors and Affiliations

  1. 1.Department of Computer SciencePurdue UniversityWest LafayetteUSA
  2. 2.GoogleMountain ViewUSA
  3. 3.Department of Computer SciencePurdue UniversityWest LafayetteUSA

Personalised recommendations