WikiDetect: Automatic Vandalism Detection On Wikipedia
Journal Title: Romanian Journal of Human - Computer Interaction - Year 2011, Vol 4, Issue 2
Abstract
Article vandalism has always been one of the greatest security issues of Wikipedia, yet few automatic (non-human) solutions for this problem have been developed so far. Large amounts of time are spent by volunteers correcting vandalized edits, instead of using this time to add quality content to Wikipedia articles. The purpose of this paper is to introduce a new vandalism detection system, based on a machine learning technique trained on a corpus of real data, and to test its performance. The application functions in a very realistic environment, as it analyzes expert annotated wikitext, extracted from the encyclopedia’s database, which is used to evaluate different vandalism detection algorithms. The paper presents a critical analysis of the obtained results, comparing them to existing solutions, and suggests different statistical classification methods that bring improvements to the system.
Authors and Affiliations
Dan Cioiu, Traian Eugen Rebedea
Keywords
Related Articles
- EP ID EP28853
- DOI -
- Views 404
- Downloads 11
Ranking of comments published on YouTube using natural language processing techniques
Publishing of comments is a form of interaction that has become an important part of the Social Web phenomenon. Comments are enhancing online interaction, however their visualization and ranking becomes extremely difficu...
Evaluation Of Motivational Value Of An Augmented Reality System For Learning Biology
The development of augmented reality (AR) technologies creates new opportunities and challenges for e-learning systems designers. An important goal of these new platforms is increasing the learning motivation of students...
Facial Expression Recognition Based on Computer-Vision Specific Methods
The automatic, computerized recognition of the emotional states based on the facial expression represents an important step towards the elimination of the communication gaps that exist between the man and the machine. Th...
The ergonomic quality of an educational application based on augmented reality – a measurement model with causal indicators
In recent years the educational applications based on augmented reality (AR) gained interest due to the opportunities provided by the integration of real objects from the traditional didactics on a hardware-software plat...
Ignoring Irrelevant Information on Displays
This paper presents empirical and modeling work aiming to contribute toward a coherent theory of how humans select relevant information and discharge irrelevant information presented on displays. Two empirical studies ar...