phenomenon · claim-type · cross-domain-transfer · mechanism · claim-relation · replication-status · limitation — grounded in the full text| phenomenon | political delegitimization discourse— “Political Delegitimization Discourse (PDD) is defined as discourse that seeks to undermine the legitimacy of political identities through attacks against their symbolic aspects, rather than criticizing specific policies or actions.” | |
| claim-type | method— “In this paper, we propose Political Delegitimization Discourse (PDD) as a distinct analytical category and introduce a computational pipeline for its large-scale detection and characterization.” | |
| method — evidence | — “We introduce a twostage classification pipeline, and benchmark finetuned encoder models and decoder LLMs.” | |
| transfer | from natural language processing: transformer encoder models (multilingual mBERT, and the Hebrew-targeted AlephBERT and HeRO) and LLM decoders, applied to detect political delegitimization discourse in Knesset and social media text— “For encoders, we use the multilingual mBERT (Devlin et al., 2019), and Hebrew-targeted encoders AlephBERT (Seker et al., 2022), HeRO (Shalumov and Haskey, 2023) and the base and large variants of DictaBERT (Shmidman et al., 2023).” | transfers[0] |
| transfer | from political methodology (Monroe, Colaresi and Quinn 2008): the weighted log-odds method for identifying tokens most strongly associated with a group, applied to political blocs— “Using the weighted log odds method proposed by Monroe et al. (2008), we identify the PDD target tokens most strongly associated with each political bloc.” | transfers[1] |
| mechanism | a two-stage pipeline: a binary classifier first decides whether a sentence carries PDD at all, and only sentences it marks positive go on to be classified for properties and target spans— “We model PDD as a two-stage pipeline: 1. Binary PDD classifier. Encoders are trained with three types of loss: default, class weights and focal loss (Lin et al., 2017), and decoders are trained to produce a Hebrew True/False label. 2. 2nd stage tasks (only where PDD=1). (a) Multi-task classifier for properties of PDD. Encoder models are… | mechanisms[0] |
| mechanism | the category is drawn by what the utterance DOES to the target's standing rather than by whether it is rude, and the paper says this is why classifiers built on surface hostility miss the subtle cases— “PDD differs fundamentally from incivility, hate speech and toxicity: it is defined not by the presence of profanity or insults but by its symbolic goal of denying an actor’s right to political inclusion; it is not solely about the how something is said (e.g., whether it is rude or offensive), but rather about what it does: denies the… | mechanisms[1] |
| mechanism | the boundary against policy criticism is enforced by a worked NEGATIVE example rather than by a rule— “Importantly, critique or negative attitudes towards policy issues is not in itself a sufficient condition for PDD, even if phrased in harsh terms. For example, the sentence “This [budget] is an example of negligence and promiscuous conduct, endangering both the economy and society in Israel.” is not annotated as PDD.” | mechanisms[2] |
| mechanism | every proportion is computed by aggregating at the SPEAKER level first, so that prolific politicians cannot dominate the rate— “For all analyses, the proportions were computed by first aggregating at the speaker level to avoid over-weighting more active politicians.” | mechanisms[3] |
| mechanism | distinctive targets per political bloc are identified with a weighted log-odds method rather than by raw frequency— “Using the weighted log odds method proposed by Monroe et al. (2008), we identify the PDD target tokens most strongly associated with each political bloc.” | mechanisms[4] |
| builds-on | Rivlin-Angert (2025), on delegitimization of political identities— “The objective of PDD is to establish political dominance and suppress alternative narratives by narrowing the boundaries of acceptable discourse and excluding specific ideas and ideologies from being considered legitimate (Rivlin-Angert, 2025).” | claim_relations[0] |
| builds-on | Mor-Lan et al. (2024), IsraParlTweet dataset of Knesset speeches— “We utilize the Isra- ParlTweet dataset (Mor-Lan et al., 2024), a full archive of Knesset floor speeches from 1992-2023.” | claim_relations[1] |
| builds-on | Monroe et al. (2008), weighted log odds method— “Using the weighted log odds method proposed by Monroe et al. (2008), we identify the PDD target tokens most strongly associated with each political bloc.” | claim_relations[2] |
| extends | existing NLP tasks: toxicity detection, stance detection, targeted sentiment analysis— “Our work extends beyond existing NLP tasks such as toxicity detection, stance detection, and targeted sentiment analysis.” | claim_relations[3] |
| sense | PDD - A STIPULATED CATEGORY WHOSE BOUNDARY IS SYMBOL VERSUS POLICY: hostility toward a political actor counts only when it is not grounded in policy critique, so the same anger about the same target falls inside or outside the category depending on what the coder judges it to be aimed at— “sentence is considered positive for PDD if it targets a political actor, group, or institution and conveys a hostile characterization not grounded in policy critique but in symbol-based delegitimization” | senses[0] |
| sense | the boundary, SHOWN RATHER THAN STATED: the paper prints a sentence calling a budget an example of negligence and promiscuous conduct endangering the economy and society, and records that it is NOT annotated as PDD - a published negative case, which is rarer in this corpus than a definition— “For example, the sentence “This [budget] is an example of negligence and… | senses[1] |
| sense | the conceptual definition BEHIND the annotation scheme: discourse aimed at discrediting political groups or actors by attacking their symbolic and affective dimensions - the scheme is built on that phrase, and every count in the paper inherits it | senses[2] |
| control | the annotated dataset split 70 per cent train, 15 per cent validation, 15 per cent test — held — rules out reporting classifier performance on data used to fit or to select it - the three-way split separates fitting, model choice and reporting Quotation withheld — this paper is not ours to reproduce, and the page has already quoted as much of it as the rights layer allows. The tag, its field and its confidence stand; the sentence is at the publisher. | controls[0] |
| edge | PDD —same-as→ Political Delegitimization Discourse Quotation withheld — this paper is not ours to reproduce, and the page has already quoted as much of it as the rights layer allows. The tag, its field and its confidence stand; the sentence is at the publisher. | concept_edges[0] |
| edge | PDD —distinct-from→ policy critique Quotation withheld — this paper is not ours to reproduce, and the page has already quoted as much of it as the rights layer allows. The tag, its field and its confidence stand; the sentence is at the publisher. | concept_edges[1] |
| outcome (stated by the tagger, no quotation) | control — held | controls[0] |
| for which use | limitation — any count of delegitimizing speech from this corpus: a sentence counts only if the hostile characterization is not grounded in policy critique but in symbol-based delegitimization, which is a judgement made per sentence Quotation withheld — this paper is not ours to reproduce, and the page has already quoted as much of it as the rights layer allows. The tag, its field and its confidence stand; the sentence is at the publisher. | limitations[4] |
| for which use | limitation — the reliability of the labels underlying these results: annotation was by three human annotators including the lead author, with agreement measured on a sample of 170 sentences Quotation withheld — this paper is not ours to reproduce, and the page has already quoted as much of it as the rights layer allows. The tag, its field and its confidence stand; the sentence is at the publisher. | limitations[5] |
| for which use | limitation — claims here about intensity, incivility, target type or affective framing: those annotations exist for 642 instances, against 1,812 sentences exhibiting the phenomenon in a corpus of 10,410 Quotation withheld — this paper is not ours to reproduce, and the page has already quoted as much of it as the rights layer allows. The tag, its field and its confidence stand; the sentence is at the publisher. | limitations[6] |
| for which use | limitation — treating PDD as an established construct: it is proposed in this paper as a distinct analytical category alongside the pipeline built to detect it Quotation withheld — this paper is not ours to reproduce, and the page has already quoted as much of it as the rights layer allows. The tag, its field and its confidence stand; the sentence is at the publisher. | limitations[7] |
| replication | untested | |
| limitation | The study's scope and transferability are limited. Quotation withheld — this paper is not ours to reproduce, and the page has already quoted as much of it as the rights layer allows. The tag, its field and its confidence stand; the sentence is at the publisher. | limitations[0] |
| limitation | Findings from the Hebrew-language, Israeli case may not generalize to other languages or political systems. Quotation withheld — this paper is not ours to reproduce, and the page has already quoted as much of it as the rights layer allows. The tag, its field and its confidence stand; the sentence is at the publisher. | limitations[1] |
| limitation | The social media analysis covers only Facebook posts from 2018-2021, excluding other platforms and later periods. Quotation withheld — this paper is not ours to reproduce, and the page has already quoted as much of it as the rights layer allows. The tag, its field and its confidence stand; the sentence is at the publisher. | limitations[2] |
| limitation | Porting the approach to other languages and political contexts is expected to be difficult because delegitimization is shaped by local dynamics. Quotation withheld — this paper is not ours to reproduce, and the page has already quoted as much of it as the rights layer allows. The tag, its field and its confidence stand; the sentence is at the publisher. | limitations[3] |
| limitation | The category is defined by excluding policy criticism, a line a coder must draw in each sentence. Quotation withheld — this paper is not ours to reproduce, and the page has already quoted as much of it as the rights layer allows. The tag, its field and its confidence stand; the sentence is at the publisher. | limitations[4] |
| limitation | Reliability was established on a 170-sentence sample by coders who include the study's lead author. Quotation withheld — this paper is not ours to reproduce, and the page has already quoted as much of it as the rights layer allows. The tag, its field and its confidence stand; the sentence is at the publisher. | limitations[5] |
| limitation | Only a sixth of the labelled corpus carries the finer annotations the characterisation rests on. Quotation withheld — this paper is not ours to reproduce, and the page has already quoted as much of it as the rights layer allows. The tag, its field and its confidence stand; the sentence is at the publisher. | limitations[6] |
| limitation | The category is proposed by this paper rather than inherited from the literature. Quotation withheld — this paper is not ours to reproduce, and the page has already quoted as much of it as the rights layer allows. The tag, its field and its confidence stand; the sentence is at the publisher. | limitations[7] |
finding · quantity · variable · definition · key-term — grounded in the full text| finding | Delegitimization intensity was rated on a three-point scale. Quotation withheld — this paper is not ours to reproduce, and the page has already quoted as much of it as the rights layer allows. The tag, its field and its confidence stand; the sentence is at the publisher. | content_tags.findings[0] |
| evidence status note | finding — QUOTE RECOVERED FROM THE PAPER'S OWN CHARACTERS. The recorded quote was LETTERS-ONLY IDENTICAL to this stretch of the staged text but not an exact substring of it - spaces, hyphens, ligature glyphs or mathematical operators differed, so it could never anchor. This is the file's own text between the same two letters: not produced by a rule about the damage, copied out of the file. Round-trip checked (the recovered span is letters-only equal to the original) and length-checked. The text as originally recorded is kept in evidence as extracted. | content_tags.findings[0] |
| finding | Early computational approaches used supervised classifiers to detect abusive language aimed at politicians. Quotation withheld — this paper is not ours to reproduce, and the page has already quoted as much of it as the rights layer allows. The tag, its field and its confidence stand; the sentence is at the publisher. | content_tags.findings[1] |
| key-terms | delegitimization, annotation, classification, parliamentary speech, polarization, Hebrew corpus |
| concept | Political Delegitimization Discourse Quotation withheld — this paper is not ours to reproduce, and the page has already quoted as much of it as the rights layer allows. The tag, its field and its confidence stand; the sentence is at the publisher. | concepts[5] |
| concept | PDD Quotation withheld — this paper is not ours to reproduce, and the page has already quoted as much of it as the rights layer allows. The tag, its field and its confidence stand; the sentence is at the publisher. | concepts[6] |
| concept | policy critique Quotation withheld — this paper is not ours to reproduce, and the page has already quoted as much of it as the rights layer allows. The tag, its field and its confidence stand; the sentence is at the publisher. | concepts[7] |
| concept | incivility Quotation withheld — this paper is not ours to reproduce, and the page has already quoted as much of it as the rights layer allows. The tag, its field and its confidence stand; the sentence is at the publisher. | concepts[8] |
| concept | annotation scheme Quotation withheld — this paper is not ours to reproduce, and the page has already quoted as much of it as the rights layer allows. The tag, its field and its confidence stand; the sentence is at the publisher. | concepts[9] |
| inter-coder reliability on a 170-sentence sample: average correlation 0.91 and average Cohen's Kappa 0.82, called substantial agreement | Quotation withheld — this paper is not ours to reproduce, and the page has already quoted as much of it as the rights layer allows. The tag, its field and its confidence stand; the sentence is at the publisher. | content_tags.statistics[0] |
| the rise in parliamentary PDD: mean share 6.6% to 9.8%, reported with t = -105.24 and p < 0.01 alongside |d| = 0.13 | Quotation withheld — this paper is not ours to reproduce, and the page has already quoted as much of it as the rights layer allows. The tag, its field and its confidence stand; the sentence is at the publisher. | content_tags.statistics[1] |
| the gender difference: 0.066 against 0.055, called modest in the same sentence as significant, t = 2.613, p = 0.010, |d| = 0.268 | Quotation withheld — this paper is not ours to reproduce, and the page has already quoted as much of it as the rights layer allows. The tag, its field and its confidence stand; the sentence is at the publisher. | content_tags.statistics[2] |
| the corpus: 10,410 annotated sentences, 1,812 PDD-positive at 17.4%, and 642 carrying the second-stage annotations | Quotation withheld — this paper is not ours to reproduce, and the page has already quoted as much of it as the rights layer allows. The tag, its field and its confidence stand; the sentence is at the publisher. | content_tags.statistics[3] |
When we have changed our mind. Some entries in the table begin with a word in capitals and the reason for it. EVIDENCE CORRECTED — the finding still stands, but we had quoted the wrong sentence from the paper, and the quotation has been replaced with the right one. RETRACTED — the entry itself was wrong; it stays on the page, marked, with the reason, rather than being deleted. WITHDRAWN AND REPLACED — the entry was wrong, and a corrected version of it appears in the entries below. Each mark carries its own reason, in brackets, because the reasons differ from one entry to the next. An entry we have WITHDRAWN is removed from this page and kept in the record, with its reason. A line reading Audit and a date is a later re-reading of the entry against its whole sentence: DOUBTFUL means it was kept, and the reason says what is loose about it. Quotation marks inside the tagger's sentence. Where a tag is the tagger's own sentence, a phrase in quotation marks inside it is borrowed from the paper — the tagger's wording around it is not. The paper's own sentence is the evidence quote for that row; on this page it is withheld with the article, and the article is at its publisher. Nothing inside quotation marks anywhere on this page is ours: if it is quoted, it is the paper's. Whose words a concept carries. A concept entry records a term the paper itself uses, so the term, the sense given for it, and its evidence are the paper's own words, quoted where the paper fixes them. This is the opposite of a sense entry in the tag table, which is the tagger's sentence about how the paper uses a term. Where a concept entry could not be grounded in the paper's words, the entry says so on its own row.
Tag layer © the Meta-Tagging Project, CC BY 4.0. The paper text is © its authors/publisher
and is linked, not reproduced. Excerpts shown are short quotations for identification and verification.
· back to index
· concepts · authors
· עברית
© 2026 Shir Sivroni · ORCID 0009-0000-2597-2824