Not All Comments Are Equal: Insights into Comment Moderation from a Topic-Aware Model

Elaine Zosa, Ravi Shekhar, Mladen Karan, Matthew Purver


Abstract
Moderation of reader comments is a significant problem for online news platforms. Here, we experiment with models for automatic moderation, using a dataset of comments from a popular Croatian newspaper. Our analysis shows that while comments that violate the moderation rules mostly share common linguistic and thematic features, their content varies across the different sections of the newspaper. We therefore make our models topic-aware, incorporating semantic features from a topic model into the classification decision. Our results show that topic information improves the performance of the model, increases its confidence in correct outputs, and helps us understand the model’s outputs.
Anthology ID:
2021.ranlp-1.185
Volume:
Proceedings of the International Conference on Recent Advances in Natural Language Processing (RANLP 2021)
Month:
September
Year:
2021
Address:
Held Online
Venue:
RANLP
SIG:
Publisher:
INCOMA Ltd.
Note:
Pages:
1652–1662
Language:
URL:
https://aclanthology.org/2021.ranlp-1.185
DOI:
Bibkey:
Cite (ACL):
Elaine Zosa, Ravi Shekhar, Mladen Karan, and Matthew Purver. 2021. Not All Comments Are Equal: Insights into Comment Moderation from a Topic-Aware Model. In Proceedings of the International Conference on Recent Advances in Natural Language Processing (RANLP 2021), pages 1652–1662, Held Online. INCOMA Ltd..
Cite (Informal):
Not All Comments Are Equal: Insights into Comment Moderation from a Topic-Aware Model (Zosa et al., RANLP 2021)
Copy Citation:
PDF:
https://aclanthology.org/2021.ranlp-1.185.pdf
Code
 ezosa/topic-aware-moderation