TY - GEN
T1 - Aggression Detection in Social Media
T2 - COLING 2018 - 1st Workshop on Trolling, Aggression and Cyberbullying, TRAC 2018 - Proceedings of the Workshop
AU - Aroyehun, Segun Taofeek
AU - Gelbukh, Alexander
N1 - Publisher Copyright:
© COLING 2018 - 1st Workshop on Trolling, Aggression and Cyberbullying, TRAC 2018 - Proceedings of the Workshop.
PY - 2018
Y1 - 2018
N2 - With the advent of the read-write web which facilitates social interactions in online spaces, the rise of anti-social behaviour in online spaces has attracted the attention of researchers. In this paper, we address the challenge of automatically identifying aggression in social media posts. Our team, saroyehun, participated in the English track of the Aggression Detection in Social Media Shared Task. On this task, we investigate the efficacy of deep neural network models of varying complexity. Our results reveal that deep neural network models require more data points to do better than an NBSVM linear baseline based on character n-grams. Our improved deep neural network models were trained on augmented data and pseudo labeled examples. Our LSTM classifier receives a weighted macro-F1 score of 0.6425 to rank first overall on the Facebook sub-task of the shared task. On the social media sub-task, our CNN-LSTM model records a weighted macro-F1 score of 0.5920 to place third overall.
AB - With the advent of the read-write web which facilitates social interactions in online spaces, the rise of anti-social behaviour in online spaces has attracted the attention of researchers. In this paper, we address the challenge of automatically identifying aggression in social media posts. Our team, saroyehun, participated in the English track of the Aggression Detection in Social Media Shared Task. On this task, we investigate the efficacy of deep neural network models of varying complexity. Our results reveal that deep neural network models require more data points to do better than an NBSVM linear baseline based on character n-grams. Our improved deep neural network models were trained on augmented data and pseudo labeled examples. Our LSTM classifier receives a weighted macro-F1 score of 0.6425 to rank first overall on the Facebook sub-task of the shared task. On the social media sub-task, our CNN-LSTM model records a weighted macro-F1 score of 0.5920 to place third overall.
UR - http://www.scopus.com/inward/record.url?scp=85122301091&partnerID=8YFLogxK
M3 - Contribución a la conferencia
AN - SCOPUS:85122301091
T3 - COLING 2018 - 1st Workshop on Trolling, Aggression and Cyberbullying, TRAC 2018 - Proceedings of the Workshop
SP - 90
EP - 97
BT - COLING 2018 - 1st Workshop on Trolling, Aggression and Cyberbullying, TRAC 2018 - Proceedings of the Workshop
PB - Association for Computational Linguistics (ACL)
Y2 - 25 August 2018
ER -