Deep learning based sentiment analysis and offensive language identification on multilingual code-mixed data

K Shanmugavadivel, VE Sathishkumar, S Raja… - Scientific Reports, 2022 - nature.com
Sentiment analysis is a process in Natural Language Processing that involves detecting and
classifying emotions in texts. The emotion is focused on a specific thing, an object, an …

Aggression and misogyny detection using BERT: A multi-task approach

NS Samghabadi, P Patwa, S Pykl… - Proceedings of the …, 2020 - aclanthology.org
In recent times, the focus of the NLP community has increased towards offensive language,
aggression, and hate-speech detection. This paper presents our system for TRAC-2 shared …

Bagging BERT models for robust aggression identification

J Risch, R Krestel - Proceedings of the Second Workshop on …, 2020 - aclanthology.org
Modern transformer-based models with hundreds of millions of parameters, such as BERT,
achieve impressive results at text classification tasks. This also holds for aggression …

Tackling online abuse: A survey of automated abuse detection methods

P Mishra, H Yannakoudakis, E Shutova - ar** a new classifier for automated identification of incivility in social media
S Davidson, Q Sun, M Wojcieszak - Proceedings of the fourth …, 2020 - aclanthology.org
Incivility is not only prevalent on online social media platforms, but also has concrete effects
on individual users, online groups, and the platforms themselves. Given the prevalence and …

Speech emotion recognition among elderly individuals using multimodal fusion and transfer learning

G Boateng, T Kowatsch - … of the 2020 International Conference on …, 2020 - dl.acm.org
Recognizing the emotions of the elderly is important as it could give an insight into their
mental health. Emotion recognition systems that work well on the elderly could be used to …

Technology acceptance and transparency demands for toxic language classification–interviews with moderators of public online discussion fora

LK Wilms, K Gerl, A Stoll, M Ziegele - Human–Computer …, 2024 - Taylor & Francis
Many online discussion providers consider using algorithm-based moderation software to
support their employees in moderating toxic communication. Such technology is also …