Home > Research > Publications & Outputs > Publish or Hold?

Electronic data

Links

View graph of relations

Publish or Hold?: Automatic Comment Moderation in Luxembourgish News Articles

Research output: Contribution in Book/Report/Proceedings - With ISBN/ISSNConference contribution/Paperpeer-review

Published

Standard

Publish or Hold? Automatic Comment Moderation in Luxembourgish News Articles. / Ranasinghe, Tharindu; Plum, Alistair; Purschke, Christoph et al.
Proceedings of the 14th International Conference on Recent Advances in Natural Language Processing: RANLP 2023. ed. / Galia Angelova; Maria Kunilovskaya; Ruslan Mitkov. Varna: INCOMA Ltd, 2023. p. 968-978.

Research output: Contribution in Book/Report/Proceedings - With ISBN/ISSNConference contribution/Paperpeer-review

Harvard

Ranasinghe, T, Plum, A, Purschke, C & Zampieri, M 2023, Publish or Hold? Automatic Comment Moderation in Luxembourgish News Articles. in G Angelova, M Kunilovskaya & R Mitkov (eds), Proceedings of the 14th International Conference on Recent Advances in Natural Language Processing: RANLP 2023. INCOMA Ltd, Varna, pp. 968-978, 14th Conference on Recent Advances in Natural Language Processing , Varna, Bulgaria, 4/09/23. <https://aclanthology.org/2023.ranlp-1.104/>

APA

Ranasinghe, T., Plum, A., Purschke, C., & Zampieri, M. (2023). Publish or Hold? Automatic Comment Moderation in Luxembourgish News Articles. In G. Angelova, M. Kunilovskaya, & R. Mitkov (Eds.), Proceedings of the 14th International Conference on Recent Advances in Natural Language Processing: RANLP 2023 (pp. 968-978). INCOMA Ltd. https://aclanthology.org/2023.ranlp-1.104/

Vancouver

Ranasinghe T, Plum A, Purschke C, Zampieri M. Publish or Hold? Automatic Comment Moderation in Luxembourgish News Articles. In Angelova G, Kunilovskaya M, Mitkov R, editors, Proceedings of the 14th International Conference on Recent Advances in Natural Language Processing: RANLP 2023. Varna: INCOMA Ltd. 2023. p. 968-978

Author

Ranasinghe, Tharindu ; Plum, Alistair ; Purschke, Christoph et al. / Publish or Hold? Automatic Comment Moderation in Luxembourgish News Articles. Proceedings of the 14th International Conference on Recent Advances in Natural Language Processing: RANLP 2023. editor / Galia Angelova ; Maria Kunilovskaya ; Ruslan Mitkov. Varna : INCOMA Ltd, 2023. pp. 968-978

Bibtex

@inproceedings{428bee3059134993ac2d20864fcab254,
title = "Publish or Hold?: Automatic Comment Moderation in Luxembourgish News Articles",
abstract = "Recently, the internet has emerged as the primary platform for accessing news. In the majority of these news platforms, the users now have the ability to post comments on news articles and engage in discussions on various social media. While these features promote healthy conversations among users, they also serve as a breeding ground for spreading fake news, toxic discussions and hate speech. Moderating or removing such content is paramount to avoid unwanted consequences for the readers. How- ever, apart from a few notable exceptions, most research on automatic moderation of news article comments has dealt with English and other high resource languages. This leaves under-represented or low-resource languages at a loss. Addressing this gap, we perform the first large-scale qualitative analysis of more than one million Luxembourgish comments posted over the course of 14 years. We evaluate the performance of state-of-the-art transformer models in Luxembourgish news article comment moderation. Furthermore, we analyse how the language of Luxembourgish news article comments has changed over time. We observe that machine learning models trained on old comments do not perform well on recent data. The findings in this work will be beneficial in building news comment moderation systems for many low-resource languages",
author = "Tharindu Ranasinghe and Alistair Plum and Christoph Purschke and Marcos Zampieri",
year = "2023",
month = sep,
day = "4",
language = "English",
pages = "968--978",
editor = "Galia Angelova and Maria Kunilovskaya and Ruslan Mitkov",
booktitle = "Proceedings of the 14th International Conference on Recent Advances in Natural Language Processing",
publisher = "INCOMA Ltd",
note = "14th Conference on Recent Advances in Natural Language Processing , RANLP 2023 ; Conference date: 04-09-2023 Through 06-09-2023",
url = "http://ranlp.org/ranlp2023/",

}

RIS

TY - GEN

T1 - Publish or Hold?

T2 - 14th Conference on Recent Advances in Natural Language Processing

AU - Ranasinghe, Tharindu

AU - Plum, Alistair

AU - Purschke, Christoph

AU - Zampieri, Marcos

PY - 2023/9/4

Y1 - 2023/9/4

N2 - Recently, the internet has emerged as the primary platform for accessing news. In the majority of these news platforms, the users now have the ability to post comments on news articles and engage in discussions on various social media. While these features promote healthy conversations among users, they also serve as a breeding ground for spreading fake news, toxic discussions and hate speech. Moderating or removing such content is paramount to avoid unwanted consequences for the readers. How- ever, apart from a few notable exceptions, most research on automatic moderation of news article comments has dealt with English and other high resource languages. This leaves under-represented or low-resource languages at a loss. Addressing this gap, we perform the first large-scale qualitative analysis of more than one million Luxembourgish comments posted over the course of 14 years. We evaluate the performance of state-of-the-art transformer models in Luxembourgish news article comment moderation. Furthermore, we analyse how the language of Luxembourgish news article comments has changed over time. We observe that machine learning models trained on old comments do not perform well on recent data. The findings in this work will be beneficial in building news comment moderation systems for many low-resource languages

AB - Recently, the internet has emerged as the primary platform for accessing news. In the majority of these news platforms, the users now have the ability to post comments on news articles and engage in discussions on various social media. While these features promote healthy conversations among users, they also serve as a breeding ground for spreading fake news, toxic discussions and hate speech. Moderating or removing such content is paramount to avoid unwanted consequences for the readers. How- ever, apart from a few notable exceptions, most research on automatic moderation of news article comments has dealt with English and other high resource languages. This leaves under-represented or low-resource languages at a loss. Addressing this gap, we perform the first large-scale qualitative analysis of more than one million Luxembourgish comments posted over the course of 14 years. We evaluate the performance of state-of-the-art transformer models in Luxembourgish news article comment moderation. Furthermore, we analyse how the language of Luxembourgish news article comments has changed over time. We observe that machine learning models trained on old comments do not perform well on recent data. The findings in this work will be beneficial in building news comment moderation systems for many low-resource languages

M3 - Conference contribution/Paper

SP - 968

EP - 978

BT - Proceedings of the 14th International Conference on Recent Advances in Natural Language Processing

A2 - Angelova, Galia

A2 - Kunilovskaya, Maria

A2 - Mitkov, Ruslan

PB - INCOMA Ltd

CY - Varna

Y2 - 4 September 2023 through 6 September 2023

ER -