Cultural Shift or Linguistic Drift? Comparing Two Computational Measures of Semantic Change
Open accessThe DOI matches its Crossref record; 17 of the 17 references it cites were found in a registry or an index.
Abstract
Words shift in meaning for many reasons, including cultural factors like new technologies and regular linguistic processes like subjectification.Understanding the evolution of language and culture requires disentangling these underlying causes.Here we show how two different distributional measures can be used to detect two different types of semantic change.The first measure, which has been used in many previous works, analyzes global shifts in a word's distributional semantics; it is sensitive to changes due to regular processes of linguistic drift, such as the semantic generalization of promise ("I promise."→"Itpromised to be exciting.").The second measure, which we develop here, focuses on local changes to a word's nearest semantic neighbors; it is more sensitive to cultural shifts, such as the change in the meaning of cell ("prison cell" → "cell phone").Comparing measurements made by these two methods allows researchers to determine whether changes are more cultural or linguistic in nature, a distinction that is essential for work in the digital humanities and historical linguistics.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Distributed Representations of Words and Phrases and their Compositionality
Mikolov, T., Sutskever, I., Chen, K., Corrado, G., & Dean, J. (2013) · arXiv · doi:10.48550/arxiv.1310.4546 · Cited by 24,533 · cited 1×
“Table 2 lists these words with some representative historical contexts (Davies, 2010).”
BackgroundFrom Frequency to Meaning: Vector Space Models of Semantics
Turney, P. D., & Pantel, P. (2010) · Journal of Artificial Intelligence Research · doi:10.1613/jair.2934 · Cited by 2,866
Regularity in semantic change: A view from a sociocultural perspective
(2024) · Cognitive Linguistic Studies in Cultural Contexts · doi:10.1075/clscc.15.c10 · Cited by 1,263
Diachronic Word Embeddings Reveal Statistical Laws of Semantic Change
Hamilton, W. L., Leskovec, J., & Jurafsky, D. (2016) · Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · doi:10.18653/v1/p16-1141 · Cited by 943
Self-citationSyntactic Annotations for the Google Books NGram Corpus
Lin, Y., Michel, J., Aiden, E. L., Orwant, J., Brockman, W., & Petrov, S. (2012) · Cited by 423
Statistically Significant Detection of Linguistic Change
Kulkarni, V., Al-Rfou, R., Perozzi, B., & Skiena, S. (2015) · Proceedings of the 24th International Conference on World Wide Web · doi:10.1145/2736277.2741627 · Cited by 390 · cited 1×
“Distributional methods of embedding words in vector spaces according to their co-occurrence statistics are a promising new tool for diachronic semantics (Gulordava and Baroni, 2011; Jatowt and Duh, 2014; Kulkarni et al., 2014; Xu and Kemp, 2015; Hamilton et al., 2016).”
MethodMetaphor comprehension: A computational theory
Kintsch, W. (2000) · Psychonomic Bulletin & Review · doi:10.3758/bf03212981 · Cited by 353 · cited 1×
“Sensitivity to shifts in verbs (and other predicates) indicates a propensity to capture regular processes of linguistic drift (Gentner and France, 1988; Kintsch, 2000; Traugott and Dasher, 2001).”
BackgroundTemporal Analysis of Language through Neural Language Models
Kim, Y., Chiu, Y.-I., Hanaki, K., Hegde, D., & Petrov, S. (2014) · Proceedings of the ACL 2014 Workshop on Language Technologies and Computational Social Science · doi:10.3115/v1/w14-2517 · Cited by 305 · cited 2×
“Global measure The first measure analyzes global shifts in a word’s vector semantics and is identical to the measure used in most previous works (Gulordava and Baroni, 2011; Jatowt and Duh, 2014; Kim et al., 2014; Hamilton et al., 2016).”
ResultGeneralized Linear Mixed Models
McCulloch, C. E. (2001) · Encyclopedia of Environmetrics · doi:10.1002/9780470057339.vag009 · Cited by 295
Gulordava, K., & Baroni, M. (2011) · Cited by 164
Cited by
Word embeddings quantify 100 years of gender and ethnic stereotypes
Garg, N., Schiebinger, L., Jurafsky, D., & Zou, J. (2018) · Proceedings of the National Academy of Sciences · doi:10.1073/pnas.1720347115 · Cited by 1,065
“However, this literature primarily studies semantic changes, such as how the word gay used to primarily mean cheerful and now means predominantly means homosexual (26, 52), and does not investigate bias.”
BackgroundSelf-citationCan Large Language Models Transform Computational Social Science?
Ziems, C., Held, W., Shaikh, O., Chen, J., Zhang, Z., & Yang, D. (2023) · arXiv · doi:10.48550/arxiv.2305.03514 · Cited by 839
Can Large Language Models Transform Computational Social Science?
Ziems, C., Held, W., Shaikh, O., Chen, J., Zhang, Z., & Yang, D. (2024) · Computational Linguistics · doi:10.1162/coli_a_00502 · Cited by 585
A Timely Intervention: Tracking the Changing Meanings of Political Concepts with Word Vectors
Rodman, E. (2020) · Political Analysis · doi:10.1017/pan.2019.23 · Cited by 112
“Hamilton et al. (2016b), for instance, assess their models using a (for our purposes insu iciently granular) directionality measure: does the model detect the right direction of semantic movement in a small set of known examples (e.g. does the word “gay” move away from the word “happy” and toward…”
BackgroundMethodInfluentialDiachronic Usage Relatedness (DURel): A Framework for the Annotation of Lexical Semantic Change
Schlechtweg, D., Schulte im Walde, S., & Eckmann, S. (2018) · Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 2 (Short Papers) · doi:10.18653/v1/n18-2027 · Cited by 77
“We see an increasing interest in the automatic detection of semantic change in computational linguistics (Hamilton et al., 2016; Frermann and La-pata, 2016; Schlechtweg et al., 2017, i.a.), motivated by expected performance improvements of practical NLP applications, or theoretical interest in…”
BackgroundSimple, Interpretable and Stable Method for Detecting Words with Usage Change across Corpora
Gonen, H., Jawahar, G., Seddah, D., & Goldberg, Y. (2020) · Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics · doi:10.18653/v1/2020.acl-main.51 · Cited by 59
“The most prominent method for detecting usage change is that of Hamilton et al. (2016b), originally applied to detect shifts in dominant word senses across time.”
InfluentialHistorical Ink: Semantic Shift Detection for 19th Century Spanish
Montes, T., Manrique-Gómez, L., & Manrique, R. (2024) · arXiv · doi:10.48550/arxiv.2407.12852
“Hamilton et al. (2016) first proposed using these embeddings for the SSD task by employing di-achronic word2vec static embeddings to measure word meaning changes across consecutive decades.”
Method
Metadata
- Authors
- Hamilton, W. L., Leskovec, J., & Jurafsky, D.
- Venue
- Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing
- Published
- 2016
- Volume
- 2016
- Pages
- 2116-2121
- OpenAlex
- W2963099212
- Cited by
- 235
- References
- 17
- FWCI
- 343.24
- Type
- conference paper
- Language
- en
- Open access
- hybrid
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.