Generating Counter Narratives against Online Hate Speech: Data and Strategies

Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pages 1177–1190 July 5 - 10, 2020. c⃝2020 Association for Computational Linguistics 1177 Generating Counter Narratives against Online Hate Speech: Data and Strategies Serra Sinem Tekiro˘glu1, Yi-Ling Chung1,2, and Marco Guerini1 1Fondazione Bruno Kessler, Via Sommarive 18, Povo, Trento, Italy 2University of Trento, Italy tekiroglu@fbk.eu,ychung@fbk.eu,guerini@fbk.eu Abstract Recently research has started focusing on avoiding undesired effects that come with content moderation, such as censorship and overblocking, when dealing with hatred on- line. The core idea is to directly intervene in the discussion with textual responses that are meant to counter the hate content and prevent it from further spreading. Accordingly, au- tomation strategies, such as natural language generation, are beginning to be investigated. Still, they suffer from the lack of sufficient amount of quality data and tend to produce generic/repetitive responses. Being aware of the aforementioned limitations, we present a study on how to collect responses to hate ef- fectively, employing large scale unsupervised language models such as GPT-2 for the gen- eration of silver data, and the best annotation strategies/neural architectures that can be used for data filtering before expert validation/post- editing. 1 Introduction Owing to the upsurge in the use of social media platforms over the past decade, Hate Speech (HS) has become a pervasive issue by spreading quickly and widely. Meanwhile, it is difficult to track and control its diffusion, since nuances in cultures and languages make it difficult to provide a clear-cut distinction between hate and dangerous speeches (Schmidt and Wiegand, 2017). The standard ap- proaches to prevent online hate spreading include the suspension of user accounts or deletion of hate comments from the social media platforms (SMPs), paving the way for the accusation of censorship and overblocking. Alternatively, to weigh the right to freedom of speech, shadow-banning has been put into use where the content/account is not deleted but hidden from SMP search results. Still, we believe that we must overstep reactive identify- and-delete strategies to responsively intervene in the conversations (Bielefeldt et al., 2011; Jurgens et al., 2019). In this line of action, some Non- Govermental Organizations (NGOs) train operators to intervene in online hateful conversations by writ- ing counter-narratives. A Counter-Narrative (CN) is a non-aggressive response that offers feedback through fact-bound arguments and is considered as the most effective approach to withstand hate mes- sages (Benesch, 2014; Schieb and Preuss, 2016). To be effective, a CN should follow guidelines sim- ilar to those provided in the ‘Get the Trolls Out’ project1, in order to avoid escalating the hatred in the discussion. Still, manual intervention against hate speech is not scalable. Therefore, data-driven NLG ap- proaches are beginning to be investigated to assist NGO operators in writing CNs. As a necessary first step, diverse CN collection strategies have been proposed, each of which has its advantages and shortcomings (Mathew et al., 2018; Qian et al., 2019; Chung et al., 2019). In this study, we aim to investigate methods to obtain high quality CNs …

Content truncated to 500 words