--- title: "Online antisemitism across platforms — paper by Smedt (2021)" description: "The report addresses the difficulty of finding antisemitic content in the growing volume of social media data, where… 6 references, cited by 1 paper here." authors: ["Tom De Smedt"] year: 2021 venue: "arXiv:2112.07783 · Textgain Technical Reports 7 (2021)" source: "https://arxiv.org/abs/2112.07783" doi: "10.48550/arxiv.2112.07783" arxiv: "2112.07783" licence: "arXiv — non-exclusive license to distribute" licence_url: "http://arxiv.org/licenses/nonexclusive-distrib/1.0/" summary_licence: "Elamur Cosmic License" canonical: "https://research.elamur.ai/free/en/papers/smedt-2021-online-antisemitism-across-platforms/" --- [Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/smedt-2021-online-antisemitism-across-platforms/) [home](https://md.research.elamur.ai/free/en/) / [papers](https://md.research.elamur.ai/free/en/papers/) / [2021](https://md.research.elamur.ai/free/en/papers/2021/page/7/) / Online antisemitism across platforms # Online antisemitism across platforms **Authors:** Tom De Smedt · **Year:** 2021 · **Venue:** arXiv:2112.07783 · Textgain Technical Reports 7 (2021) · **Licence:** [arXiv — non-exclusive license to distribute](http://arxiv.org/licenses/nonexclusive-distrib/1.0/) **Links:** [Publisher's page](https://arxiv.org/abs/2112.07783) · [PDF](https://arxiv.org/pdf/2112.07783) · [DOI 10.48550/arxiv.2112.07783](https://doi.org/10.48550/arxiv.2112.07783) · [arXiv 2112.07783](https://arxiv.org/abs/2112.07783) · [OpenAlex](https://openalex.org/W4226401635) **Citations:** 0 citations (OpenAlex, 2026-10-14) · 1 in our library, of the 141,840 papers whose bibliographies we read ## Summary The report addresses the difficulty of finding antisemitic content in the growing volume of social media data, where conspiracy narratives, partly driven by COVID-19, are spreading again. The author built a curated lexicon of more than 2,000 English and German words and multiword patterns. Each entry carries a 0–4 toxicity rating from two annotators and any number of labels covering rhetorical categories. On top of the lexicon, a transparent system gives each message a 0–100 score from the entries it matches, including variant word forms. It also highlights the matched spans so that a human can see the basis for the score. To check the system, the author ran it on five corpora where antisemitism was expected to be rare or common. The resulting ranking matched those expectations, from a mainstream 2015 baseline up to the unmoderated forum 8chan. The work matters because explainable, quickly updatable tools are needed for monitoring hate across platforms and for high-stakes moderation decisions. ## Key points - The lexicon combines several kinds of entries: - Nazi-era vocabulary such as Lügenpresse and Umvolkung. - Dehumanizing adjective plus target pairs, and violent verb plus target pairs. - Alt-right coinages such as holocough and Jewbacca. - Coded numerals such as 14/88 and HH. - Conspiracy terms such as blood libel and Vril. - Entries can carry 10+ labels, for example RIDICULE, DEHUMANIZATION, VIOLENCE and CONSPIRACY. In the annotation tool these appear as four-letter codes such as FOOL, SCUM and KILL. - Measured average toxicity and share of antisemitic posts per corpus: | Corpus | Size | Avg. toxicity | Antisemitic posts | |---|---|---|---| | Twitter/Facebook, 2015 | 100K | ~2/100 | \<0.1% | | QAnon on Twitter, late 2020 | 100K | 10/100 | ~3% | | QAnon on Twitter, early 2021 | 100K | 5/100 | ~0.5% | | Gab, 2020 | 10K | 20/100 | 8.5% | | 8chan, 2020 | 100K | 30/100 | 15% | - The author offers two explanations for the post-Capitol-riot drop: - Twitter suspended Trump and about 70,000 QAnon accounts. - Remaining users masked their language or moved to Gab and Telegram. - Additional algorithms anonymize messages for GDPR compliance. The system processes thousands of messages in minutes and can be extended through weak supervision. ## Interesting ideas - The system is validated by checking whether scores order corpora the way prior knowledge predicts, rather than against a hand-labelled test set; this is cheap and works where gold labels are scarce. - Lexicon entries are compositional patterns (a dehumanizing adjective or a violent verb joined to a target group) with graded scores and multiple labels, and the explanation is simply the matched span. - Annotators work with short mnemonic four-letter label codes, which speeds tagging and lowers cognitive load during curation. - A pseudo-random baseline sample was obtained from platform APIs by querying for punctuation marks or common vowels, giving a neutral reference corpus without topic bias. - The lexicon tracks coded and evolving vocabulary (number codes, blended neologisms) and is meant to be updated continually, because users mask language once they are watched. ## For Mova How these ideas could serve Mova, our small open language model — its files, stages and tests: - **I1** (learn): Evaluation with negative controls could likewise rank corpora expected to differ (e.g., children's fables vs. news) and flag any component whose ordering contradicts expectations. - **I2** (frames): The same idea could be lifted from surface n-grams to frames, detecting a violence-class VerbNet predicate whose patient is a social group and citing that frame as the explanation for an aggression or hostility judgement. - **I3** (learn): Compact mnemonic tags could simplify the label sets given to human checkers or LLM teacher tiers when they review silver data. - **I4** (learn): A similar trick could produce unbiased background corpora for calibrating parser confidence or measuring domain drift. - **I5** (tokens): The tokenizer and morphology could recognize numeric codes and portmanteau blends as units, linking them to known lemmas instead of splitting them into opaque fragments. *Our summary of the paper, in our own words — not its text. The work belongs to its authors; read it at the links above.* 📚 Shelves (4): [🖥️ Computer Science](https://md.research.elamur.ai/free/en/shelves/computer-science/) · 9,086 works · [🤖 Artificial Intelligence](https://md.research.elamur.ai/free/en/shelves/computer-science/artificial-intelligence/) · 8,889 works · [🤝 Social Sciences](https://md.research.elamur.ai/free/en/shelves/social-sciences/) · 744 works · [🤝 Sociology and Political Science](https://md.research.elamur.ai/free/en/shelves/social-sciences/sociology-and-political-science/) · 221 works ## Cite Cite as: Tom De Smedt. 2021. Online antisemitism across platforms. arXiv:2112.07783 · Textgain Technical Reports 7 (2021). The paper itself, not this page. BibTeX from the library's record of the work. ```bibtex @misc{smedt2021online, title = {{Online antisemitism across platforms}}, author = {Tom {De Smedt}}, year = {2021}, doi = {10.48550/arxiv.2112.07783}, eprint = {2112.07783}, archivePrefix = {arXiv}, url = {https://doi.org/10.48550/arxiv.2112.07783} } ``` - [← previous On the treatment of super-heavy syllables in Arabic Dialects: an Optimality Theoretic approach to historical typology](https://md.research.elamur.ai/free/en/papers/bokhari-2021-treatment-super-heavy-syllables-arabic/) - [next → Overcoming the challenges in morphological annotation of Turkish in universal dependencies framework](https://md.research.elamur.ai/free/en/papers/bedir-2021-overcoming-challenges-morphological-annotation-turkish/) - [↑ back to papers of 2021](https://md.research.elamur.ai/free/en/papers/2021/page/7/) ## References 6 references, 0 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet. 1. Lakomy, M. (2017). Cracks in the online “caliphate”. Perspectives on terrorism, 11(3), 40-53. [find](https://scholar.google.com/scholar?q=Lakomy%2C+M%2E+%282017%29%2E+Cracks+in+the+online+%E2%80%9Ccaliphate%E2%80%9D%2E+Perspectives+on+terrorism%2C+11%283%29%2C+40%2D53%2E) 2. Pratt, D. (2016). Islam as feared other: perception and reaction. In Fear of Muslims? (pp. 31-43). Springer. [↗](https://doi.org/10.1007/978-3-319-29698-2_3) 3. Flood, A. (2016). “‘Post-truth’ named word of the year by Oxford Dictionaries’. The Guardian. [find](https://scholar.google.com/scholar?q=Flood%2C+A%2E+%282016%29%2E+%E2%80%9C%E2%80%98Post%2Dtruth%E2%80%99+named+word+of+the+year+by+Oxford+Dictionaries%E2%80%99%2E+The+Guardian%2E) 4. Amarasingam, A., & Argentino, M. A. (2020). The QAnon conspiracy theory: A security threat in the making. CTC Sentinel, 13(7), 37-44. [find](https://scholar.google.com/scholar?q=Amarasingam%2C+A%2E%2C+%26+Argentino%2C+M%2E+A%2E+%282020%29%2E+The+QAnon+conspiracy+theory%3A+A+security+threat+in+the+making%2E+CTC+Sentinel%2C+13%287%29%2C+37%2D44%2E) 5. Dunst, C. ( 2018). “Is QAnon, the latest pro-Trump conspiracy theory, anti-Semitic?”. Haaretz. [find](https://scholar.google.com/scholar?q=Dunst%2C+C%2E+%28+2018%29%2E+%E2%80%9CIs+QAnon%2C+the+latest+pro%2DTrump+conspiracy+theory%2C+anti%2DSemitic%3F%E2%80%9D%2E+Haaretz%2E) 6. Ingram, D. (2018). “Attacks on Jewish people rising on Instagram and Twitter, researchers say”. NBC. [find](https://scholar.google.com/scholar?q=Ingram%2C+D%2E+%282018%29%2E+%E2%80%9CAttacks+on+Jewish+people+rising+on+Instagram+and+Twitter%2C+researchers+say%E2%80%9D%2E+NBC%2E) *Updated 24 October 2026*