TY  - JOUR
A1  - Risch, Julian
A1  - Krestel, Ralf
A2  - Agarwal, Basant
A2  - Nayak, Richi
A2  - Mittal, Namita
A2  - Patnaik, Srikanta
T1  - Toxic comment detection in online discussions
T2  - Deep learning-based approaches for sentiment analysis
N2  - Comment sections of online news platforms are an essential space to express opinions and discuss political topics. In contrast to other online posts, news discussions are related to particular news articles, comments refer to each other, and individual conversations emerge. However, the misuse by spammers, haters, and trolls makes costly content moderation necessary. Sentiment analysis can not only support moderation but also help to understand the dynamics of online discussions. A subtask of content moderation is the identification of toxic comments. To this end, we describe the concept of toxicity and characterize its subclasses. Further, we present various deep learning approaches, including datasets and architectures, tailored to sentiment analysis in online discussions. One way to make these approaches more comprehensible and trustworthy is fine-grained instead of binary comment classification. On the downside, more classes require more training data. Therefore, we propose to augment training data by using transfer learning. We discuss real-world applications, such as semi-automated comment moderation and troll detection. Finally, we outline future challenges and current limitations in light of most recent research publications.
KW  - deep learning
KW  - natural language processing
KW  - user-generated content
KW  - toxic comment classification
KW  - hate speech detection
Y1  - 2020
UR  - https://publishup.uni-potsdam.de/frontdoor/index/index/docId/56631
SN  - 978-981-15-1216-2
SN  - 978-981-15-1215-5
SN  - 2524-7565
SN  - 2524-7573
SP  - 85
EP  - 109
PB  - Springer
CY  - Singapore
ER  -