Metadata-based Deep Learning to estimate the quality of Wikipedia Articles

About the Project

Wikipedia allows anyone to edit articles. Under what conditions do we declare a Wikipedia article to be of high quality? The following list of attributes are typically ascribed to quality: accuracy, readability, completeness, stability, and currency [1]. Considerable research has focused on developing automated techniques to assess articles using these criteria [2].

Wikipedia has a manual quality assessment system [3]: subject-editors do rate selected articles. But most Wikipedia articles have not been selected for quality assessment. Even those that have been selected for assessment, undergo checks only a limited number of times.

Furthermore, despite the guideline standards for the ratings, there are quality inconsistencies across the same quality grade. Given the real-time, crowd-sourced nature of Wikipedia and the uncertainty of its quality assessments, any rating may potentially be out-of-date or inconsistent.

In this PhD, the student will propose metadata-based features that will be used to train a Deep Learning model to assist the manual quality assessment system, always keeping evaluations current and consistent. The project will update previous work done by the supervisor as well as fresh work from others. The work programme will include extending quality metrics, using state-of-the-art AI LLM models to evaluate quality metrics, and building a Deep Learning model to classify with greater accuracy live articles.

Successful completion of the work will result in research publications at the highest standard and a track record for the student in the field of Machine Learning.

Funding Notes

there is no funding for this project

References

1. F. Fahimnia, M. Damerchiloo, M. Khandan, M. Eltemasi, A framework for as- sessing the quality of wikipedia articles: A meta-synthesis of the literature, International Journal of Information Science and Management (IJISM) 20 (1) (2022).
2. Wikipedia quality, URL https://wikipediaquality.com/wiki/Wikipedia_Quality
3. P. M. Moás, C. T. Lopes, Automatic quality assessment of wikipedia articles—a systematic literature review, ACM Computing Surveys 56 (4) (2023) 1–37.