Measuring Quality of Collaboratively Edited Documents: The Case of Wikipedia

Dang, Quang-Vinh; Ignat, Claudia-Lavinia

doi:10.1109/cic.2016.044

Cited by 39 publications

(52 citation statements)

References 48 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Another form of bias is the presentation by Wikipedia authors of information regarding members of their own national group in a more positive way than information about other groups (ingroup bias) [15]. In line with previous research [16,17], we hypothesize that a certain proportion of such distortions is attributable to a lack of experience on the side of the respective article's contributors.…”

Section: Wikipedia As a Resourcesupporting

confidence: 68%

See 1 more Smart Citation

Effects of Contributor Experience on the Quality of Health-Related Wikipedia Articles (Preprint)

Holtz¹,

Fetahu²,

Kimmerle³

2017

Preprint

View full text Add to dashboard Cite

ObjectiveIn our study we have hypothesized a positive effect of contributor experience on the quality of health-related Wikipedia articles. MethodsWe mined the edit history of all (as of February 2017) 18,805 articles within the domain health & fitness in the English language version of Wikipedia. We identified tags within the articles' edit histories, which indicated potential issues with regard to the respective article's quality or neutrality. Out of all of the sampled articles, 99 (0.53%) articles had at some point received at least one such tag. In our analysis we only considered those articles with a minimum of ten edits (10,265 articles in total; 96 tagged articles, 0.93%). Additionally, to test our hypothesis, we constructed contributor profiles, where a profile consisted of all the articles edited by a contributor and the corresponding number of edits contributed. Results Independent sample t-tests ConclusionsOur findings indicate an effect of contributor experience on the quality of health-related Wikipedia articles. However, the breadth of previously edited articles is a stronger predictor than the mere volume of edits. More research is needed to disentangle the different aspects of contributor experience. We discuss implications of our findings with respect to ensuring the quality of health-related information in collaborative knowledge building platforms.

show abstract

Section: Wikipedia As a Resourcesupporting

confidence: 68%

“…These tags were neutral point of view policy violation (42 cases in our sample), contradictory content (13), unbalanced content (12), confusing content (17), and inaccurate content (23). Out of all the sampled articles, 99 (0.53%) articles had received at some point at least one of the aforementioned tags.…”

Section: Methodsmentioning

confidence: 99%

Effects of Contributor Experience on the Quality of Health-Related Wikipedia Articles (Preprint)

Holtz¹,

Fetahu²,

Kimmerle³

2017

Preprint

View full text Add to dashboard Cite

show abstract

“…Deep learning approaches to predicting Wikipedia article quality have also been proposed. For example, Dang and Ignat (2016b) use a version of doc2vec (Le and Mikolov 2014) to represent articles, and feed the document embeddings into a four hidden layer neural network. Shen, Qi, and Baldwin (2017) first obtain sentence representations by averaging words within a sentence, and then apply a biLSTM (Hochreiter and Schmidhuber 1997) to learn a documentlevel representation, which is combined with hand-crafted features as side information.…”

Section: Related Workmentioning

confidence: 99%

A Joint Model for Multimodal Document Quality Assessment

Shen

Salehi

Baldwin

et al. 2019

2019 ACM/IEEE Joint Conference on Digital Libraries (JCDL)

View full text Add to dashboard Cite

The quality of a document is affected by various factors, including grammaticality, readability, stylistics, and expertise depth, making the task of document quality assessment a complex one. In this paper, we explore this task in the context of assessing the quality of Wikipedia articles and academic papers. Observing that the visual rendering of a document can capture implicit quality indicators that are not present in the document text -such as images, font choices, and visual layoutwe propose a joint model that combines the text content with a visual rendering of the document for document quality assessment. Experimental results over two datasets reveal that textual and visual features are complementary, achieving state-of-the-art results.

show abstract

“…Table 11 shows that the structure feature outperforms the other feature sets; its precision is even better than the model with all of feature sets by 3.6%. Compared with the models in existing research (Dang & Ignat, 2016a;Dalip & Cristo, 2017), stacked LSTMs with structure features demonstrate considerably better performance. Intuitively, a well-organized article tends to have high quality.…”

Section: Feature Set Importance Analysismentioning

confidence: 81%

“…Some methods are not automatic and require excessive human effort. Thus, machine-learning models, such as support vector regression (SVR) or k-nearest neighbor (KNN), have been adopted (Bykau, Korn, Srivastava, & Velegrakis, 2015;Dalip & Cristo, 2017;Dalip, Lima, Gonçalves, Cristo, & Calado, 2014;Dang & Ignat, 2016a;Ganjisaffar, Javanmardi, & Lopes, 2009;Kapugama, Lorensuhewa, & Kalyani, 2017;Sinanc & Yavanoglu, 2013). Moreover, existing methods fail to implement a comprehensive feature framework.…”

Section: Introductionmentioning

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

Measuring Quality of Collaboratively Edited Documents: The Case of Wikipedia

Cited by 39 publications

References 48 publications

Effects of Contributor Experience on the Quality of Health-Related Wikipedia Articles (Preprint)

Effects of Contributor Experience on the Quality of Health-Related Wikipedia Articles (Preprint)

A Joint Model for Multimodal Document Quality Assessment

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

Contact Info

Product

Resources

About