| 1 |
Hybrid Emoji-Based Masked Language Models for Zero-Shot Abusive Language Detection
|
|
|
|
In: EMNLP 2020 - Conference on Empirical Methods in Natural Language Processing ; https://hal.archives-ouvertes.fr/hal-02972203 ; EMNLP 2020 - Conference on Empirical Methods in Natural Language Processing, Nov 2020, Virtual, France (2020)
|
|
BASE
|
|
Show details
|
|
|
| 2 |
A Multilingual Evaluation for Online Hate Speech Detection
|
|
|
|
In: ISSN: 1533-5399 ; ACM Transactions on Internet Technology ; https://hal.archives-ouvertes.fr/hal-02972184 ; ACM Transactions on Internet Technology, Association for Computing Machinery, 2020, 20 (2), pp.1-22. ⟨10.1145/3377323⟩ (2020)
|
|
BASE
|
|
Show details
|
|
|
| 3 |
Overwhelmed by Negative Emotions? Maybe You Are Being Cyber-bullied!
|
|
|
|
In: Symposium On Applied Computing ; SAC 2019 - The 34th ACM/SIGAPP Symposium On Applied Computing ; https://hal.archives-ouvertes.fr/hal-02020829 ; SAC 2019 - The 34th ACM/SIGAPP Symposium On Applied Computing, Apr 2019, Limassol, Cyprus. ⟨10.1145/3297280.3297573⟩ (2019)
|
|
Abstract:
International audience ; With the increasing number of interactions, social media users have been vulnerable to intentional aggressive acts and cyberbullying instances. In this paper, first, we carry out a message-level cyber-bullying annotation on an Instagram dataset. Second, we use the correlations on the Instagram dataset annotated with emotion, sentiment and bullying labels. Third, we build a message-level emotion classifier automatically predicting emotion labels for each comment in the Vine bullying dataset. Fourth, we build a session-based bullying classifier with the use of n-grams, emotion, sentiment and concept-level features. For both emotion and bullying classifiers, we use Linear Support Vector Classification. Our results show that "anger" and "negative" labels have a positive correlation with the presence of bullying. Concept-level features, emotion and sentiment features in different levels contribute to the bullying classifier, especially to the bullying class. Our best performing bullying classi-fier with n-grams and concept-level features (e.g., polarity, averaged polarity intensity, moodtags and semantics features) reaches to an F1-score of 0.65 for bullying class and a macro average F1-score of 0.7520.
|
|
Keyword:
[INFO.INFO-LG]Computer Science [cs]/Machine Learning [cs.LG]; [INFO.INFO-TT]Computer Science [cs]/Document and Text Processing; [INFO]Computer Science [cs]; [SHS.LANGUE]Humanities and Social Sciences/Linguistics; [SHS]Humanities and Social Sciences; CCS CONCEPTS • Computing methodologies → Natural language processing; Cyberbullying detection; Emotion classification; Sentiment analysis; Social media
|
|
URL: https://hal.archives-ouvertes.fr/hal-02020829/file/ACM_SigConf_SAC2019_1_1.pdf
https://hal.archives-ouvertes.fr/hal-02020829/document
https://hal.archives-ouvertes.fr/hal-02020829
https://doi.org/10.1145/3297280.3297573
|
|
BASE
|
|
Hide details
|
|
|
| 4 |
Cross-Platform Evaluation for Italian Hate Speech Detection
|
|
|
|
In: CLiC-it 2019 - 6th Annual Conference of the Italian Association for Computational Linguistics ; https://hal.archives-ouvertes.fr/hal-02381152 ; CLiC-it 2019 - 6th Annual Conference of the Italian Association for Computational Linguistics, Nov 2019, Bari, Italy (2019)
|
|
BASE
|
|
Show details
|
|
|
| 5 |
InriaFBK at Germeval 2018: Identifying Offensive Tweets Using Recurrent Neural Networks
|
|
|
|
In: http://hw.oeaw.ac.at/8435-5 (2018)
|
|
BASE
|
|
Show details
|
|
|
|
|
