CoChat
Sign Up
Cited by 24Wikis in Education and CollaborationText Readability and SimplificationInformation Retrieval and Search Behavior

A Joint Model for Multimodal Document Quality Assessment

Open access
Shen, Aili, Salehi, Bahar, Baldwin, Timothy, Qi, Jianzhong·2019·2019 ACM/IEEE Joint Conference on Digital Libraries (JCDL)
DOI 10.1109/jcdl.2019.00024
Open this paper in CoChat — free accountOpen PDF

Abstract

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. 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 layout - we propose a joint model that combines the text content with a visual rendering of the document for document quality assessment. Experimental results over a Wikipedia dataset reveal that textual and visual features are complementary, achieving state-of-the-art results. Further experiments on a Peer Review dataset verify the general applicability of our proposed model.

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.1109/jcdl.2019.00024

Cites

4 of 4 references verified0 citation errors · 0 not checkable

Statistics

Claims the paper makes

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Claims other papers make about this one

Each is checked against this paper’s own text: does it say what the citing paper says it does?

  • Prior work largely treats critical text assessment as a black box, leaving unanswered how experts arrive at their judgement.

    “Yet, existing work treats critical text assessment as a black box problem, limiting interpretability and human-AI collaboration.”

    From STRICTA: Structured Reasoning in Critical Text Assessment for Peer Review and Beyond (2025) · cites this paper as Shen et al., 2019

    The Introduction says prior document-quality studies mainly focus on textual features, and Related Work describes features and models used to predict quality. Neither section says that critical text assessment is treated as a black box or that this limits interpretability or human–AI collaboration; searches for those concepts found no supporting passage in our copy. (LLM, conf=0.72)

    Experimental — accuracy not yet measured

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

The self-check needs the paper’s full text.

Cites

Flagged first, then by citations

Research works printed but not linked: 33

  1. Agichtein, E.; Castillo, C.; Donato, D.; Gionis, A.; and Mishne, G. 2008. Finding high-quality content in social media. In WSDM, 183-194.
  2. Alikaniotis, D.; Yannakoudakis, H.; and Rei, M. 2016. Automatic text scor- ing using neural networks. In ACL, 715-725.
  3. Belinkov, Y.; Mohtarami, M.; Cyphers, S.; and Glass, J. R. 2015. VectorSLU: A continu- ous word vector approach to answer selection in community question answering systems. In SemEval@NAACL-HLT, 282-287.
  4. Bengio, Y.; Ducharme, R.; Vincent, P.; and Jauvin, C. 2003. A neural probabilistic language model. Journal of Machine Learning Research 3:1137-1155.
  5. Bird, S. 2006. NLTK: the natural language toolkit. In ACL, 69-72.
  6. Chollet, F. 2017. Xception: Deep learning with depthwise separable convolutions. In CVPR, 1800- 1807.
  7. Cummins, R.; Zhang, M.; and Briscoe, T. 2016. Constrained multi-task learning for automated essay scoring. In ACL, 789-799.
  8. Dalip, D. H.; Gonc ¸alves, M. A.; Cristo, M.; and Calado, P. 2017. A general multiview framework for assessing the quality of collaboratively created content on web 2.0. Journal of the Association for Information Science and Technology 68(2):286-308.
  9. Dang and Ignat 2016a] Dang, Q.-V., and Ignat, C.-L. 2016a. Measuring quality of collaboratively edited documents: the case of Wikipedia. In The 2nd IEEE International Confer- ence on Collaboration and Internet Computing, 266-275.
  10. Dang, Q. V., and Ignat, C. 2017. An end-to-end learning solution for assessing the quality of Wikipedia articles. In Proceedings of the 13th International Symposium on Open Collaboration, 4:1-4:10.
  11. Guzmán, F.; Màrquez, L.; and Nakov, P. 2016. Machine transla- tion evaluation meets community question answering. In ACL, 460-466.
  12. Guzmán, F.; Nakov, P.; and Màrquez, L. 2016. MTE-NN at SemEval-2016 task 3: Can machine translation evaluation help community ques- tion answering? In SemEval@NAACL-HLT, 887-895.
  13. Hochreiter, S., and Schmidhuber, J. 1997. Long short-term memory. Neural Computation 9(8):1735-1780.
  14. Hou, Y.; Tan, C.; Wang, X.; Zhang, Y.; Xu, J.; and Chen, Q. 2015. HITSZ-ICRC: exploiting classifica- tion approach for answer selection in community question answering. In SemEval@NAACL-HLT, 196-202.
  15. Jeon, J.; Croft, W. B.; Lee, J. H.; and Park, S. 2006. A framework to predict the quality of answers with non-textual features. In SIGIR, 228-235.
  16. Le, Q. V., and Mikolov, T. 2014. Distributed representations of sentences and documents. In ICML, 1188-1196.
  17. Pennington, J.; Socher, R.; and Manning, C. D. 2014. GloVe: Global vectors for word representation. In EMNLP, 1532-1543.
  18. Persing, I., and Ng, V. 2013. Model- ing thesis clarity in student essays. In ACL, 260-269.
  19. Persing, I., and Ng, V. 2014. Model- ing prompt adherence in student essays. In ACL, 1534-1543.
  20. Phandi, Chai, and Ng 2015] Phandi, P.; Chai, K. M. A.; and Ng, H. T. 2015. Flexible domain adaptation for automated essay scoring using correlated linear regression. In EMNLP, 431-439.
  21. Selvaraju, R. R.; Cogswell, M.; Das, A.; Vedantam, R.; Parikh, D.; and Batra, D. 2017. Grad- cam: Visual explanations from deep networks via gradient- based localization. In ICCV, 618-626.
  22. Shen, A.; Qi, J.; and Bald- win, T. 2017. A hybrid model for quality assessment of Wikipedia articles. In Proceedings of the Australasian Lan- guage Technology Association Workshop, 43-52.
  23. Simonyan, K., and Zisser- man, A. 2014. Very deep convolutional networks for large- scale image recognition. arXiv preprint arXiv:1409.1556 abs/1409.1556. · arXiv
  24. Suggu, S. P.; Goutham, K. N.; Chin- nakotla, M. K.; and Shrivastava, M. 2016. Hand in glove: Deep feature fusion network architectures for answer quality prediction in community question answering. In COLING, 1429-1440.
  25. Suryanto, M. A.; Lim, E.; Sun, A.; and Chiang, R. H. L. 2009. Quality-aware collaborative question answering: methods and evaluation. In WSDM, 142-151.
  26. Szegedy, C.; Vanhoucke, V.; Ioffe, S.; Shlens, J.; and Wojna, Z. 2016. Rethinking the Inception architecture for computer vision. In CVPR, 2818-2826.
  27. Taghipour, K., and Ng, H. T. 2016. A neural approach to automated essay scoring. In EMNLP, 1882-1891.
  28. Tay, Y.; Phan, M. C.; Tuan, L. A.; and Hui, S. C. 2018. SkipFlow: Incorporating neural coherence fea- tures for end-to-end automatic text scoring. In AAAI.
  29. van der Maaten and Hinton 2008] van der Maaten, L., and Hinton, G. 2008. Visualizing data using t-SNE. JMLR 9:2579-2605.
  30. Warncke-Wang, M.; Ayukaev, V. R.; Hecht, B.; and Terveen, L. 2015. The success and failure of quality improvement projects in peer production communities. In Proceedings of the 18th ACM Conference on Computer Supported Cooperative Work & Social Com- puting, CSCW 2015, 743-756.
  31. Warncke-Wang, M.; Cosley, D.; and Riedl, J. 2013. Tell me more: an actionable quality model for Wikipedia. In Proceedings of the 9th International Symposium on Open Collaboration, 8:1-8:10.
  32. Yang, P.; Sun, X.; Li, W.; and Ma, S. 2018. Automatic academic paper rating based on modularized hi- erarchical convolutional neural network. In ACL, 496-502.
  33. Zhou, X.; Hu, B.; Chen, Q.; Tang, B.; and Wang, X. 2015. Answer sequence learning with neural net- works for answer selection in community question answer- ing. arXiv preprint arXiv:1506.06490. · arXiv

Cited by

Sorted by citations

Authors
Shen, A., Salehi, B., Baldwin, T., & Qi, J.
Affiliations
The University of Melbourne (AU)
ORCID
Venue
2019 ACM/IEEE Joint Conference on Digital Libraries (JCDL)
Publisher
IEEE
Published
2019-06
Pages
107-110
ISSN
1552-5996 (ISSN-L)
DOI
10.1109/jcdl.2019.00024
OpenAlex
W2967226526
Cited by
24
References
4
Citations by year
2026: 1 · 2025: 2 · 2024: 3 · 2023: 3 · 2022: 5 · 2021: 4 · 2020: 4 · 2019: 2
FWCI
14.24
Type
conference paper
Language
en
Open access
Licence
Locations
  • ACM/IEEE Joint Conference on Digital Libraries (publishedVersion)
  • arXiv (Cornell University) (submittedVersion)
  • arXiv (Cornell University)
Topics
  • Social Sciences › Communication › Wikis in Education and Collaboration
  • Physical Sciences › Computer Science › Artificial Intelligence › Text Readability and Simplification
  • Physical Sciences › Computer Science › Information Systems › Information Retrieval and Search Behavior
Keywords
document quality assessment, multimodal learning, Wikipedia articles, visual rendering, text and image fusion, readability, grammaticality, visual layout, peer review

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review