Papers › It's a Thin Line Between Love and Hate: Using the Echo in Modeling Dynamics of Racist...

It's a Thin Line Between Love and Hate: Using the Echo in Modeling Dynamics of Racist Online Communities

16 Nov 2020arXiv:2012.01133archive 2025-07-28

Eyal Arviv, Simo Hanouna, Oren Tsur

The (((echo))) symbol -- triple parenthesis surrounding a name, made it to mainstream social networks in early 2016, with the intensification of the U.S. Presidential race. It was used by members of the alt-right, white supremacists and internet trolls to tag people of Jewish heritage -- a modern incarnation of the infamous yellow badge (Judenstern) used in Nazi-Germany. Tracking this trending meme, its meaning, and its function has proved elusive for its semantic ambiguity (e.g., a symbol for a virtual hug). In this paper we report of the construction of an appropriate dataset allowing the reconstruction of networks of racist communities and the way they are embedded in the broader community. We combine natural language processing and structural network analysis to study communities promoting hate. In order to overcome dog-whistling and linguistic ambiguity, we propose a multi-modal neural architecture based on a BERT transformer and a BiLSTM network on the tweet level, while also taking into account the users ego-network and meta features. Our multi-modal neural architecture outperforms a set of strong baselines. We further show how the the use of language and network structure in tandem allows the detection of the leaders of the hate communities. We further study the ``intersectionality'' of hate and show that the antisemitic echo correlates with hate speech that targets other minority and protected groups. Finally, we analyze the role IRA trolls assumed in this network as part of the Russian interference campaign. Our findings allow a better understanding of recent manifestations of racism and the dynamics that facilitate it.

PaperPDFCode

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

naslabbgu/hate_speech_detection mentioned on GitHubtf report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

TAG

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

AdamAttentionAttention DropoutBERTBiLSTMDense ConnectionsDropoutLSTMLayer NormalizationLinear LayerLinear Warmup With Linear DecayMulti-Head AttentionResidual ConnectionSigmoid ActivationSoftmaxTanh ActivationWeight DecayWordPiece

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections