The Geometry of Culture: Analyzing the Meanings of Class through Word Embeddings

Austin C. Kozlowski, Matt Taddy, James A. Evans · American Sociological Review / arXiv · 2019 · digital-humanities · 10.1177/0003122419877135 · record kozlowski2019-geometry-culture
tag layer · index · concepts · authors · עברית

Where this record's text came from. faceted 2026-08 by reading the locally held text (pdf); every evidence string verified as an exact substring of that text before merging. IMPORTANT: the supplied file is a scrape of the Sage journal landing page, not the article. Below the ARTICLE TEXT marker it contains only the abstract, the full reference list, author biographies, site navigation/paywall boilerplate, and citation counts — there is no Methods, Results or Discussion text. Every facet here is therefore anchored in the abstract. limitations is empty because the paper's own statements of limitation (if any) are in body text that is absent from this file, not because the paper makes none. Claim relations is empty for the same reason: the file's only mentions of prior work are bare reference-list entries, which rule 2 forbids quoting and rule 7 forbids inferring relations from. The abstract's 'which we validate with surveys' is the only trace of the survey-validation study, so method is recorded from that sentence. This record should be re-done if the full text is obtained. 2026-08-14 and 2026-08-15 schema-0.3 passes: every quote verified as an exact substring of the staged text and anchored at merge time; concept terms verified present; every edge endpoint an existing node. Update, 15 September 2026: EXCEPTION, measured with the merge gate's own predicate (Paper.locate): 3 quote(s) on this record are not found as one exact string in the current staged text - content_tags.statistics[2].evidence, content_tags.statistics[4].evidence, transfers[0].evidence. The sentence above does not hold for them as written. Where a row records why - the quote is grounded in another copy of the paper, joins two passages with an ellipsis, or differs from the staged text by extraction noise - that note stays on the row. Update, 18 September 2026: the full text has since been staged (109,719 characters, the survey-validation study included) and this record's quotes now come from it - 49 of its 50 are in it, anchored as deep as character 97,531; the sentences above describe the abstract-only text this record was first read from.

5 quotes on this page carry a character that renders as nothing. 12 such characters in all: a zero-width character. The PDF this text came from used characters that survive extraction as code points no ordinary font draws, so the quote reads as though they were never there. That can change what a sentence says: a soft hyphen left by a line break puts a space inside a word, so document reads as docu ment; a flattened superscript turns 10⁹ into 109. The quotes are reproduced exactly as the extraction left them and have NOT been repaired — the meaning of such a code point belongs to the one PDF it came from, and guessing it would produce a clean, confident, unverifiable quote.

1 quote on this page was cut from a different copy of this article. This project holds two extractions of this paper: the plain text every other quote here is anchored in, and the publisher’s own HTML edition, which we are not licensed to republish. It is verbatim in the second and cannot be found in the first — not because the tagging is wrong, but because the extraction damaged the passage: a page number dropped into the middle of a number, a formula moved out of its sentence, a ligature where two letters belong. The record names the copy for each one. The quote is the paper’s; the extraction is not.

How to read this page. The article itself is not reproduced here — this paper is not cleared for redistribution, so what follows is the tag layer alone. The evidence sentences are withheld with the article. The table at the foot lists every tag the record carries; each row names the facet it belongs to, and the whose words column says whether the tag records the paper's own wording or the tagger's sentence about the paper. Every tag links to each other paper in the corpus carrying it. The machine-readable edition of the same thing is the TEI file beside this one, where the tags live in standOff, and the article is at its publisher via the link below. 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.

Other fields define these differently the same word, defined another way in another discipline
meaning 4 fields · class 3 fields · standard-deviation 3 fields · gender 2 fields · bootstrap 2 fields · confidence-interval 2 fields · and 3 more →

Tags on this paper

Every tag the record carries, each linking to every other paper in the corpus that carries it. A tag appears here whether or not its words occur in the article — the spans below are only the ones a sentence in this paper licenses. Of the 8 concept tags on this paper, 3 are grounded in a quoted sentence.

word embedding semantic space cultural dimension cosine similarity distributional semantics word embeddings semantic relations cultural categories building cultural dimensions as averaged vector-differences between antonym word pairs, then projecting words onto them vector space cultural dimensions class gender meaning corpus high-dimensional cultural associations neural-network Latent Semantic Analysis (LSA) relational model of meaning Bayesian bootstrap confidence-interval confidence intervals correlation Pearson mean mean of p-value standard-deviation standard deviation statistical-significance statistical significance variance system-or-tool-building

Legend

relation to other work	`claim_relations`	how this paper stands to another: agrees, contradicts, extends, qualifies
claim type	`claim_type`	the shape of the claim: existence, mechanism, method, critique, prediction, null
concept edge	`concept_edges`	an asserted relation between two concepts, with the sentence asserting it
concept	`concepts`	an idea the paper works with, quoted where the paper uses it
content tag	`content_tags`	a finding, definition, quantity, statistic or variable named in the paper
control	`controls`	an experiment run to eliminate a rival explanation
limitation	`limitations`	what the paper says its evidence cannot support
mechanism	`mechanisms`	how the reported effect is said to come about
method	`method`	how the paper produced its evidence
phenomenon	`phenomenon`	the effect or regularity under study
sense	`senses`	a distinct use of a term, quoted where the paper fixes it

The paper

The full text is not reproduced here. This article is not cleared for redistribution, so the page carries the tag layer only. Its evidence sentences are withheld; the grounding status remains with each tag, and the article itself is at https://doi.org/10.1177/0003122419877135. The reading view exists for the papers whose licence permits it.

Every tag on this page

claim_relations 6 · claim_type 1 · concept_edges 1 · concepts 3 · content_tags 18 · controls 1 · limitations 6 · mechanisms 1 · method 1 · phenomenon 1 · senses 3

Relations on this page carry a quotation for the claim. Where a relation was separately evidenced — and so tested against the vocabulary for its type — the row says so; none of 1 relation here carry that mark. The rest are the tagger’s reading of the sentence quoted beside them.

facet	tag	field	conf.	whose words
claim_type	method Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above.	`claim_type`		the paper's words
phenomenon	cultural dimensions in word-embedding spaces Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above.	`phenomenon`		the paper's words
method	system-or-tool-building Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: system-or-tool-building	`method`		the paper's words
mechanisms	mechanisms Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: building cultural dimensions as averaged vector-differences between antonym word pairs, then projecting words onto them	`mechanisms[0]`		the tagger's words
limitations	The method needs a large corpus; subtle and complex cultural associations cannot be recovered from small bodies of text. Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. what this limits: any application to a small corpus: WORD EMBEDDINGS ... REQUIRE A RELATIVELY LARGE BODY OF TEXT IF THE OUTPUT VECTOR SPACE IS TO CAPTURE SUBTLE AND COMPLEX ASSOCIATIONS	`limitations[0]`		the tagger's words
limitations	Race could not be traced historically because the terminology shifted across the century, so the historical analysis was restricted to gender and class. Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. what this limits: the absence of race from the historical analysis: UNDERTAKING THIS TASK EFFECTIVELY WOULD REQUIRE A DEEPER ENGAGEMENT WITH LINGUISTIC SHIFTS IN RACIAL TERMINOLOGY THAN IS FEASIBLE WITHIN THE SPACE CONSTRAINTS - the dimension is omitted for a vocabulary reason	`limitations[1]`		the tagger's words
limitations	The validating survey used a Mechanical Turk sample that is not representative of the US population. Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. what this limits: the survey validation specifically: OUR SAMPLE CANNOT BE SAID TO BE REPRESENTATIVE OF THE GENERAL POPULATION OF THE UNITED STATES	`limitations[2]`		the tagger's words
limitations	Embedding projections capture semantic association in text, not material or on-the-ground social realities. Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. what this limits: every substantive claim about culture: WORD EMBEDDINGS MODELS, BY DISTILLING INFORMATION FROM LOCAL WORD CO-OCCURRENCES, DO NOT PROVIDE DIRECT INFORMATION ABOUT MATERIAL, ON-THE-GROUND REALITIES	`limitations[3]`		the tagger's words
limitations	The confidence intervals depend on treating books and newspapers as independent draws from a population of cultural observations, which is stated as a condition rather than shown. Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. about this quote: THE QUOTE IS AN ASSUMPTION, NOT A FINDING - the sentence opens 'If we assume that the texts' before it, and a page number ('29') sits between that opening and the quote. · what this limits: the confidence or credible intervals reported for distances and projections here: they follow from assuming the underlying texts are i.i.d. observations drawn from a population of cultural observations	`limitations[4]`	1.0	the tagger's words
limitations	The method the paper displaces is criticised on reproducibility, which is the ground on which the new one is offered. Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. what this limits: the comparison between close reading and embedding-based analysis: close reading is credited with advancing the field and criticised for clear limitations in reproducibility	`limitations[5]`	1.0	the tagger's words
controls	the interpretation space sampled SYSTEMATICALLY - 1,775 antonym pairs taken from WordNet - rather than by selecting salient dimensions, with the reported dimensions restricted to those at the smallest angle to the focal ones Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. eliminates: CHERRY-PICKING BY THE ANALYST. The paper names the charge it is answering: that researchers 'conveniently cherry-pick explanations to confirm…'. An unsupervised model yields far more readable structure than any paper reports, so the choice of what to report is where the freedom lives · outcome (stated by the tagger, no quotation): held	`controls[0]`	0.95	the tagger's words
concepts	word embeddings Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: word embeddings	`concepts[5]`		the paper's words
concepts	semantic relations Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: semantic relations	`concepts[6]`		the paper's words
concepts	cultural categories Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: cultural categories	`concepts[7]`		the paper's words
senses	meaning - OPERATIONALISED AS GEOMETRY: semantic relations between words represented as geometric relationships between vectors, which the paper calls a relational model of meaning Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above.	`senses[0]`	1.0	the tagger's words
senses	semantic change - measured as CHANGE IN POSITION: a word's rate of semantic change taken to be the change in its overall position in the vector space Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above.	`senses[1]`	1.0	the tagger's words
senses	cultural categories - held by the intersectionality literature to be inseparable: their meaning changes as they overlap, so they cannot be isolated and understood independently Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above.	`senses[2]`	1.0	the tagger's words
claim_relations	builds-on → word2vec (CBOW/skip-gram) and GloVe (from NLP) Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above.	`claim_relations[0]`		the tagger's words
claim_relations	extends → interpretive text analysis of culture (adding reproducibility) Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above.	`claim_relations[1]`		the tagger's words
claim_relations	extends → Bolukbasi et al. (2016) and Caliskan et al. (2017) on bias in word embeddings Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above.	`claim_relations[2]`		the tagger's words
claim_relations	contradicts → Bolukbasi et al. (2016) proposal to de-bias word embeddings Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above.	`claim_relations[3]`		the tagger's words
claim_relations	extends → Pierre Bourdieu's relational field theory / correspondence analysis Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above.	`claim_relations[4]`		the tagger's words
claim_relations	extends → Osgood's semantic differential method Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above.	`claim_relations[5]`		the tagger's words
concept_edges	semantic relations —operationalised-as→ word embeddings Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. strength of the relation: 1 also in: semantic relations · word embeddings	`concept_edges[0]`		the tagger's words
content_tags	20th — span of the gender/class coevolution analysis Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above.	`content_tags.quantities[0]`		the tagger's words
content_tags	1970s — when LSA-type methods first appeared Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above.	`content_tags.quantities[1]`		the tagger's words
content_tags	20,000 — example vocabulary size reduced by embeddings Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above.	`content_tags.quantities[2]`		the tagger's words
content_tags	projecting words onto these dimensions recovers widely shared cultural connotations Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above.	`content_tags.findings[1]`		the tagger's words
content_tags	feminine and masculine occupations sit at opposite poles of a gender dimension Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above.	`content_tags.findings[2]`		the tagger's words
content_tags	word embeddings capture more complex semantic relations than prior text methods Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. about this quote: A PAGE NUMBER SITS INSIDE THIS QUOTE: the '2' between 'past modes of' and 'computational text analysis' is the page's number, not part of the sentence; read the quote with it deleted.	`content_tags.findings[3]`		the tagger's words
content_tags	word embeddings Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: word embeddings	`content_tags.definitions[0]`		the tagger's words
content_tags	Latent Semantic Analysis (LSA) Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: Latent Semantic Analysis (LSA)	`content_tags.definitions[1]`		the tagger's words
content_tags	relational model of meaning Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: relational model of meaning	`content_tags.definitions[2]`		the tagger's words
content_tags	Bayesian Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. about this quote: 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. also in: Bayesian	`content_tags.statistics[0]`		the tagger's words
content_tags	bootstrap Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: bootstrap	`content_tags.statistics[1]`		the tagger's words
content_tags	confidence-interval Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: confidence-interval	`content_tags.statistics[2]`		the tagger's words
content_tags	correlation Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: correlation	`content_tags.statistics[3]`		the tagger's words
content_tags	mean Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: mean	`content_tags.statistics[4]`		the tagger's words
content_tags	p-value Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. about this quote: 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. also in: p-value	`content_tags.statistics[5]`		the tagger's words
content_tags	standard-deviation Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. about this quote: 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. also in: standard-deviation	`content_tags.statistics[6]`		the tagger's words
content_tags	statistical-significance Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. about this quote: 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. also in: statistical-significance	`content_tags.statistics[7]`		the tagger's words
content_tags	variance Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: variance	`content_tags.statistics[8]`		the tagger's words

Interpretive choices

Tags that could not be placed in the text:

transfers[0] — quotation withheld — the page has already reproduced as much of this paper as the rights budget allows
NOT MACHINE-VOUCHED: not-in-our-copy - The quote is in the original web page we fetched for this paper, but not in the text we tag against, which was extracted differently. Checked with ligatures, hyphens, spacing and punctuation set aside.

What was deliberately not tagged, and why, is recorded per paper by the tagger. Where a paper has no such record, this page says so rather than implying that nothing was declined.