Joint Modelling of Emotion and Abusive Language Detection

Rajamanickam, Santhosh; Mishra, Pushkar; Yannakoudakis, Helen; Shutova, Ekaterina

doi:10.18653/v1/2020.acl-main.394

Cited by 56 publications

(40 citation statements)

References 29 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We first adapt three multi-task learning models based on bidirectional recurrent neural networks recently proposed by Rajamanickam et al (2020) for jointly modeling abusive language detection and emotion detection. We also adapt our M-RoBERTa Emo model in a multi-task setting using two variants.…”

Section: Predictive Modelsmentioning

confidence: 99%

See 1 more Smart Citation

Modeling the Severity of Complaints in Social Media

Jin¹,

Αλέτρας²

2021

Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Langua

View full text Add to dashboard Cite

The speech act of complaining is used by humans to communicate a negative mismatch between reality and expectations as a reaction to an unfavorable situation. Linguistic theory of pragmatics categorizes complaints into various severity levels based on the face-threat that the complainer is willing to undertake. This is particularly useful for understanding the intent of complainers and how humans develop suitable apology strategies. In this paper, we study the severity level of complaints for the first time in computational linguistics. To facilitate this, we enrich a publicly available data set of complaints with four severity categories and train different transformer-based networks combined with linguistic information achieving 55.7 macro F1. We also jointly model binary complaint classification and complaint severity in a multi-task setting achieving new state-of-the-art results on binary complaint detection reaching up to 88.2 macro F1. Finally, we present a qualitative analysis of the behavior of our models in predicting complaint severity levels. 1,2

show abstract

Section: Predictive Modelsmentioning

confidence: 99%

“…We adapt the MTL-Hard Sharing model of Rajamanickam et al (2020), where a single encoder is shared and updated by both tasks. We first pass GloVe embedding representations to a shared stacked BiGRU encoder.…”

Section: Mtl-hard Sharingmentioning

confidence: 99%

Modeling the Severity of Complaints in Social Media

Jin¹,

Αλέτρας²

2021

Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Langua

View full text Add to dashboard Cite

show abstract

“…Liu et al (2017) used shared and private latent features leveraging multitask learning for different text classification tasks. Rajamanickam et al (2020); Duong et al (2016); Liu et al (2016) proposed a joint framework for modeling abuse and emotion detection and showed improvements over STL and transfer learning. Akhtar et al (2018) proposed a multitask ensemble architecture for jointly modeling emotion, sentiment, and intensity, which gave improvements over single-label classification.…”

Section: Related Workmentioning

confidence: 99%

“…Such an approach to aggregate information flow from two encoders has facilitated success in prior Multitask learning settings as well (Rajamanickam et al, 2020;Dankers et al, 2019). As for our auxiliary task, we pass the embeddings e (a) through only the shared encoder (h (a) = h (s) ), followed by a dropout layer.…”

Section: Multitask Learningmentioning

confidence: 99%

Multitask Learning for Emotionally Analyzing Sexual Abuse Disclosures

Sawhney

Mathur

Jain³

et al. 2021

Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Langua

View full text Add to dashboard Cite

The #MeToo movement on social media platforms initiated discussions over several facets of sexual harassment in our society. Prior work by the NLP community for automated identification of the narratives related to sexual abuse disclosures barely explored this social phenomenon as an independent task. However, emotional attributes associated with textual conversations related to the #MeToo social movement are complexly intertwined with such narratives. We formulate the task of identifying narratives related to the sexual abuse disclosures in online posts as a joint modeling task that leverages their emotional attributes through multitask learning. Our results demonstrate that positive knowledge transfer via context-specific shared representations of a flexible cross-stitched parameter sharing model helps establish the inherent benefit of jointly modeling tasks related to sexual abuse disclosures with emotion classification from the text in homogeneous and heterogeneous settings. We show how for more domain-specific tasks related to sexual abuse disclosures such as sarcasm identification and dialogue act (refutation, justification, allegation) classification, homogeneous multitask learning is helpful, whereas for more general tasks such as stance and hate speech detection, heterogeneous multitask learning with emotion classification works better. 1

show abstract

“…Several research papers have proven that emotion lexicons are helpful features for the tasks of abusive language and hate-speech detection (Koufakou and Scott, 2020;Wiegand et al, 2018;Martins et al, 2018;Corazza et al, 2018;Alorainy et al, 2018;Gao and Huang, 2017). There is also one study that shows jointly modeling of emotion classification and abuse detection, through a multitask approach, can improve the performance of the latter task (Rajamanickam et al, 2020).…”

Section: Related Workmentioning

confidence: 99%

Attending the Emotions to Detect Online Abusive Language

Samghabadi¹,

Hatami²,

Shafaei³

et al. 2020

Proceedings of the Fourth Workshop on Online Abuse and Harms

View full text Add to dashboard Cite

In recent years, abusive behavior has become a serious issue in online social networks. In this paper, we present a new corpus for the task of abusive language detection that is collected from a semi-anonymous online platform, and unlike the majority of other available resources, is not created based on a specific list of bad words. We also develop computational models to incorporate emotions into textual cues to improve aggression identification. We evaluate our proposed methods on a set of corpora related to the task and show promising results with respect to abusive language detection.

show abstract

Joint Modelling of Emotion and Abusive Language Detection

Cited by 56 publications

References 29 publications

Modeling the Severity of Complaints in Social Media

Modeling the Severity of Complaints in Social Media

Multitask Learning for Emotionally Analyzing Sexual Abuse Disclosures

Attending the Emotions to Detect Online Abusive Language

Contact Info

Product

Resources

About