Quality Assessment of Wikipedia Articles without Feature Engineering

Dang, Quang-Vinh; Ignat, Claudia-Lavinia

doi:10.1145/2910896.2910917

Cited by 57 publications

(49 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…We showed that in addition to studying the structure-based features by analyzing the content of the articles in terms of their readability, a higher accuracy and information gain can be obtained compared with other approaches. As a future direction of our work we plan to combine manual feature design with automatic feature extraction from deep learning techniques [62] in order to improve classification performance.…”

Section: Discussionmentioning

confidence: 99%

Measuring Quality of Collaboratively Edited Documents: The Case of Wikipedia

Dang

Ignat

2016

2016 IEEE 2nd International Conference on Collaboration and Internet Computing (CIC)

Self Cite

View full text Add to dashboard Cite

Abstract-Wikipedia is a great example of large scale collaboration, where people from all over the world together build the largest and maybe the most important human knowledge repository in the history. However, a number of studies showed that the quality of Wikipedia articles is not equally distributed. While many articles are of good quality, many others need to be improved. Assessing the quality of Wikipedia articles is very important for guiding readers towards articles of high quality and suggesting authors and reviewers which articles need to be improved. Due to the huge size of Wikipedia, an effective automatic assessment method to measure Wikipedia articles quality is needed.In this paper, we present an automatic assessment method of Wikipedia articles quality by analyzing their content in terms of their format features and readability scores. Our results show improvements both in terms of accuracy and information gain compared with other existing approaches.

show abstract

Section: Discussionmentioning

confidence: 99%

Measuring Quality of Collaboratively Edited Documents: The Case of Wikipedia

Dang

Ignat

2016

2016 IEEE 2nd International Conference on Collaboration and Internet Computing (CIC)

Self Cite

View full text Add to dashboard Cite

show abstract

“…With the development of deep-learning models, some researchers have attempted to apply deep-learning models to the quality assessment of Wikipedia. Doc2Vec was used to represent Wikipedia articles, and a DNN was applied to classify the article quality (Dang & Ignat, 2016b). Although Doc2Vec was used to automatically extract features, ensuring that Doc2Vec acquires the important features that contribute most to quality classification is difficult.…”

Section: Deep-learning-based Quality Assessment Methodsmentioning

confidence: 99%

“…However, this feature framework only partially focuses on the information of each article. Doc2Vec was used to automatically generate features and directly represent Wikipedia articles (Dang & Ignat, 2016b). Those authors also applied Doc2Vec to the raw content of Wikipedia articles instead of applying Doc2Vec to the text after process (Dang & Ignat, 2016c).…”

Section: Feature Frameworkmentioning

confidence: 99%

Assessing the quality of information on wikipedia: A deep‐learning approach

Wang

2019

Asso for Info Science & Tech

View full text Add to dashboard Cite

Currently, web document repositories have been collaboratively created and edited. One of these repositories, Wikipedia, is facing an important problem: assessing the quality of Wikipedia. Existing approaches exploit techniques such as statistical models or machine leaning algorithms to assess Wikipedia article quality. However, existing models do not provide satisfactory results. Furthermore, these models fail to adopt a comprehensive feature framework. In this article, we conduct an extensive survey of previous studies and summarize a comprehensive feature framework, including text statistics, writing style, readability, article structure, network, and editing history. Selected state-of-the-art deep-learning models, including the convolutional neural network (CNN), deep neural network (DNN), long short-term memory (LSTMs) network, CNN-LSTMs, bidirectional LSTMs, and stacked LSTMs, are applied to assess the quality of Wikipedia. A detailed comparison of deep-learning models is conducted with regard to different aspects: classification performance and training performance. We include an importance analysis of different features and feature sets to determine which features or feature sets are most effective in distinguishing Wikipedia article quality. This extensive experiment validates the effectiveness of the proposed model.

show abstract

“…There are also a few works that try to combine metrics from articles content and edition history [16,17].…”

Section: Related Workmentioning

confidence: 99%

“…Although existing works propose various sets of metrics for assessing quality of Wikipedia articles, there is no universal feature set for this task [17]. Additional challenge is to consider different language versions, which can have different quality models [4,5].…”

Section: Related Workmentioning

confidence: 99%

Relative Quality and Popularity Evaluation of Multilingual Wikipedia Articles

Lewoniewski¹,

Węcel²,

Abramowicz³

2017

Preprint

View full text Add to dashboard Cite

Despite the fact that Wikipedia is often criticized for its poor quality, it continues to be one of the most popular knowledge base in the world. Articles in this free encyclopedia on various topics can be created and edited in about 300 different language versions independently. Our research showed that in language sensitive topics quality of information can be relatively better in the relevant language versions. However, in most cases it is difficult for the Wikipedia readers to determine the language affiliation of the described subject. Additionally, each language edition of Wikipedia can have own rules in manual assessing of the content quality. This makes automatic quality comparison of articles between various languages a challenging task. The paper presents results of relative quality and popularity assessment of over 28 million articles in 44 selected language versions. In addition, a comparative analysis of the quality and popularity of articles in some topics was conducted. The proposed method allows to find articles with information of better quality that can be used to automatically enrich other language editions of Wikipedia.

show abstract

Quality Assessment of Wikipedia Articles without Feature Engineering

Cited by 57 publications

References 20 publications

Measuring Quality of Collaboratively Edited Documents: The Case of Wikipedia

Measuring Quality of Collaboratively Edited Documents: The Case of Wikipedia

Assessing the quality of information on wikipedia: A deep‐learning approach

Relative Quality and Popularity Evaluation of Multilingual Wikipedia Articles

Contact Info

Product

Resources

About