The Cinderella Complex: Word embeddings reveal gender stereotypes in movies and books.
Ontology highlight
ABSTRACT:
SUBMITTER: Xu H
PROVIDER: S-EPMC6874350 | biostudies-literature | 2019
REPOSITORIES: biostudies-literature
Publications
The Cinderella Complex: Word embeddings reveal gender stereotypes in movies and books.
Xu Huimin H Zhang Zhang Z Wu Lingfei L Wang Cheng-Jun CJ
PloS one 20191122 11
Our analysis of thousands of movies and books reveals how these cultural products weave stereotypical gender roles into morality tales and perpetuate gender inequality through storytelling. Using the word embedding techniques, we reveal the constructed emotional dependency of female characters on male characters in stories. We call this narrative structure "Cinderella complex", which assumes that women depend on men in the pursuit of a happy, fulfilling life. Our analysis covers a substantial po ...[more]
Similar Datasets
Project description:Word embeddings are a powerful machine-learning framework that represents each English word by a vector. The geometric relationship between these vectors captures meaningful semantic relationships between the corresponding words. In this paper, we develop a framework to demonstrate how the temporal dynamics of the embedding helps to quantify changes in stereotypes and attitudes toward women and ethnic minorities in the 20th and 21st centuries in the United States. We integrate word embeddings trained on 100 y of text data with the US Census to show that changes in the embedding track closely with demographic and occupation shifts over time. The embedding captures societal shifts-e.g., the women's movement in the 1960s and Asian immigration into the United States-and also illuminates how specific adjectives and occupations became more closely associated with certain populations over time. Our framework for temporal analysis of word embedding opens up a fruitful intersection between machine learning and quantitative social science.
| S-EPMC5910851 | biostudies-literature
Project description:In Western societies, the stereotype prevails that pink is for girls and blue is for boys. A third possible gendered colour is red. While liked by women, it represents power, stereotypically a masculine characteristic. Empirical studies confirmed such gendered connotations when testing colour-emotion associations or colour preferences in males and females. Furthermore, empirical studies demonstrated that pink is a positive colour, blue is mainly a positive colour, and red is both a positive and a negative colour. Here, we assessed if the same valence and gender connotations appear in widely available written texts (Wikipedia and newswire articles). Using a word embedding method (GloVe), we extracted gender and valence biases for blue, pink, and red, as well as for the remaining basic colour terms from a large English-language corpus containing six billion words. We found and confirmed that pink was biased towards femininity and positivity, and blue was biased towards positivity. We found no strong gender bias for blue, and no strong gender or valence biases for red. For the remaining colour terms, we only found that green, white, and brown were positively biased. Our finding on pink shows that writers of widely available English texts use this colour term to convey femininity. This gendered communication reinforces the notion that results from research studies find their analogue in real word phenomena. Other findings were either consistent or inconsistent with results from research studies. We argue that widely available written texts have biases on their own, because they have been filtered according to context, time, and what is appropriate to be reported.
| S-EPMC8168888 | biostudies-literature
Project description:The so-called "gender-equality paradox" is the fact that gender segregation across occupations is more pronounced in more egalitarian and more developed countries. Some scholars have explained this paradox by the existence of deeply rooted or intrinsic gender differences in preferences that materialize more easily in countries where economic constraints are more limited. In line with a strand of research in sociology, we show instead that it can be explained by cross-country differences in essentialist gender norms regarding math aptitudes and appropriate occupational choices. To this aim, we propose a measure of the prevalence and extent of internalization of the stereotype that "math is not for girls" at the country level. This is done using individual-level data on the math attitudes of 300,000 15-y-old female and male students in 64 countries. The stereotype associating math to men is stronger in more egalitarian and developed countries. It is also strongly associated with various measures of female underrepresentation in math-intensive fields and can therefore entirely explain the gender-equality paradox. We suggest that economic development and gender equality in rights go hand-in-hand with a reshaping rather than a suppression of gender norms, with the emergence of new and more horizontal forms of social differentiation across genders.
| S-EPMC7733804 | biostudies-literature
Project description:Stereotypes exist in the interactions between different social groups, and gender stereotypes are particularly prevalent. Previous studies have suggested that the medial prefrontal cortex (mPFC) is involved in the social cognition that plays an important role in gender stereotypes, but the specific causal effect of the mPFC remains controversial. In this study, we aimed to use transcranial direct current stimulation (tDCS) to identify a direct link between the mPFC and gender bias. Implicit stereotypes were measured by the gender implicit association test (IAT), and explicit prejudice was measured by the Ambivalent Sexism Inventory (ASI). We found that male and female participants had different behavioral and neural correlates of gender stereotypes. Anodal tDCS significantly reduced male participants' gender D-IAT scores compared with cathodal and sham stimulation, while the stimulation had an insignificant effect in female participants. The reduction in male participants' gender bias mainly resulted from a decrease in the difference in reaction time (RT) between congruent and incongruent blocks. Regarding the explicit bias measurement, male and female participants had distinct attitudes, but tDCS had no effect on ASI. Our results revealed that the mPFC played a causal role in controlling implicit gender stereotypes, which is consistent with previous observations and complements past lesion, neuroimaging, and transcranial magnetic stimulation (TMS) studies and suggests that males and females have different neural bases for gender stereotypes.
| S-EPMC6889476 | biostudies-literature
Project description:OBJECTIVE:In this work, we introduce a privacy technique for anonymizing clinical notes that guarantees all private health information is secured (including sensitive data, such as family history, that are not adequately covered by current techniques). MATERIALS AND METHODS:We employ a new "random replacement" paradigm (replacing each token in clinical notes with neighboring word vectors from the embedding space) to achieve 100% recall on the removal of sensitive information, unachievable with current "search-and-secure" paradigms. We demonstrate the utility of this paradigm on multiple corpora in a diverse set of classification tasks. RESULTS:We empirically evaluate the effect of our anonymization technique both on upstream and downstream natural language processing tasks to show that our perturbations, while increasing security (ie, achieving 100% recall on any dataset), do not greatly impact the results of end-to-end machine learning approaches. DISCUSSION:As long as current approaches utilize precision and recall to evaluate deidentification algorithms, there will remain a risk of overlooking sensitive information. Inspired by differential privacy, we sought to make it statistically infeasible to recreate the original data, although at the cost of readability. We hope that the work will serve as a catalyst to further research into alternative deidentification methods that can address current weaknesses. CONCLUSION:Our proposed technique can secure clinical texts at a low cost and extremely high recall with a readability trade-off while remaining useful for natural language processing classification tasks. We hope that our work can be used by risk-averse data holders to release clinical texts to researchers.
| S-EPMC7309261 | biostudies-literature
Project description:BackgroundThere has been increasing interest in machine learning based natural language processing (NLP) methods in radiology; however, models have often used word embeddings trained on general web corpora due to lack of a radiology-specific corpus.PurposeWe examined the potential of Radiopaedia to serve as a general radiology corpus to produce radiology specific word embeddings that could be used to enhance performance on a NLP task on radiological text.Materials and methodsEmbeddings of dimension 50, 100, 200, and 300 were trained on articles collected from Radiopaedia using a GloVe algorithm and evaluated on analogy completion. A shallow neural network using input from either our trained embeddings or pre-trained Wikipedia 2014 + Gigaword 5 (WG) embeddings was used to label the Radiopaedia articles. Labeling performance was evaluated based on exact match accuracy and Hamming loss. The McNemar's test with continuity and the Benjamini-Hochberg correction and a 5×2 cross validation paired two-tailed t-test were used to assess statistical significance.ResultsFor accuracy in the analogy task, 50-dimensional (50-D) Radiopaedia embeddings outperformed WG embeddings on tumor origin analogies (p < 0.05) and organ adjectives (p < 0.01) whereas WG embeddings tended to outperform on inflammation location and bone vs. muscle analogies (p < 0.01). The two embeddings had comparable performance on other subcategories. In the labeling task, the Radiopaedia-based model outperformed the WG based model at 50, 100, 200, and 300-D for exact match accuracy (p < 0.001, p < 0.001, p < 0.01, and p < 0.05, respectively) and Hamming loss (p < 0.001, p < 0.001, p < 0.01, and p < 0.05, respectively).ConclusionWe have developed a set of word embeddings from Radiopaedia and shown that they can preserve relevant medical semantics and augment performance on a radiology NLP task. Our results suggest that the cultivation of a radiology-specific corpus can benefit radiology NLP models in the future.
| S-EPMC7856086 | biostudies-literature
Project description:Distributed word representations have become an essential foundation for biomedical natural language processing (BioNLP), text mining and information retrieval. Word embeddings are traditionally computed at the word level from a large corpus of unlabeled text, ignoring the information present in the internal structure of words or any information available in domain specific structured resources such as ontologies. However, such information holds potentials for greatly improving the quality of the word representation, as suggested in some recent studies in the general domain. Here we present BioWordVec: an open set of biomedical word vectors/embeddings that combines subword information from unlabeled biomedical text with a widely-used biomedical controlled vocabulary called Medical Subject Headings (MeSH). We assess both the validity and utility of our generated word embeddings over multiple NLP tasks in the biomedical domain. Our benchmarking results demonstrate that our word embeddings can result in significantly improved performance over the previous state of the art in those challenging tasks.
| S-EPMC6510737 | biostudies-literature
Project description:BackgroundWord embeddings have been prevalently used in biomedical Natural Language Processing (NLP) applications due to the ability of the vector representations being able to capture useful semantic properties and linguistic relationships between words. Different textual resources (e.g., Wikipedia and biomedical literature corpus) have been utilized in biomedical NLP to train word embeddings and these word embeddings have been commonly leveraged as feature input to downstream machine learning models. However, there has been little work on evaluating the word embeddings trained from different textual resources.MethodsIn this study, we empirically evaluated word embeddings trained from four different corpora, namely clinical notes, biomedical publications, Wikipedia, and news. For the former two resources, we trained word embeddings using unstructured electronic health record (EHR) data available at Mayo Clinic and articles (MedLit) from PubMed Central, respectively. For the latter two resources, we used publicly available pre-trained word embeddings, GloVe and Google News. The evaluation was done qualitatively and quantitatively. For the qualitative evaluation, we randomly selected medical terms from three categories (i.e., disorder, symptom, and drug), and manually inspected the five most similar words computed by embeddings for each term. We also analyzed the word embeddings through a 2-dimensional visualization plot of 377 medical terms. For the quantitative evaluation, we conducted both intrinsic and extrinsic evaluation. For the intrinsic evaluation, we evaluated the word embeddings' ability to capture medical semantics by measruing the semantic similarity between medical terms using four published datasets: Pedersen's dataset, Hliaoutakis's dataset, MayoSRS, and UMNSRS. For the extrinsic evaluation, we applied word embeddings to multiple downstream biomedical NLP applications, including clinical information extraction (IE), biomedical information retrieval (IR), and relation extraction (RE), with data from shared tasks.ResultsThe qualitative evaluation shows that the word embeddings trained from EHR and MedLit can find more similar medical terms than those trained from GloVe and Google News. The intrinsic quantitative evaluation verifies that the semantic similarity captured by the word embeddings trained from EHR is closer to human experts' judgments on all four tested datasets. The extrinsic quantitative evaluation shows that the word embeddings trained on EHR achieved the best F1 score of 0.900 for the clinical IE task; no word embeddings improved the performance for the biomedical IR task; and the word embeddings trained on Google News had the best overall F1 score of 0.790 for the RE task.ConclusionBased on the evaluation results, we can draw the following conclusions. First, the word embeddings trained from EHR and MedLit can capture the semantics of medical terms better, and find semantically relevant medical terms closer to human experts' judgments than those trained from GloVe and Google News. Second, there does not exist a consistent global ranking of word embeddings for all downstream biomedical NLP applications. However, adding word embeddings as extra features will improve results on most downstream tasks. Finally, the word embeddings trained from the biomedical domain corpora do not necessarily have better performance than those trained from the general domain corpora for any downstream biomedical NLP task.
| S-EPMC6585427 | biostudies-literature
Project description:Increased interest in the use of word embeddings, such as word representation, for biomedical named entity recognition (BioNER) has highlighted the need for evaluations that aid in selecting the best word embedding to be used. One common criterion for selecting a word embedding is the type of source from which it is generated; that is, general (e.g., Wikipedia, Common Crawl), or specific (e.g., biomedical literature). Using specific word embeddings for the BioNER task has been strongly recommended, considering that they have provided better coverage and semantic relationships among medical entities. To the best of our knowledge, most studies have focused on improving BioNER task performance by, on the one hand, combining several features extracted from the text (for instance, linguistic, morphological, character embedding, and word embedding itself) and, on the other, testing several state-of-the-art named entity recognition algorithms. The latter, however, do not pay great attention to the influence of the word embeddings, and do not facilitate observing their real impact on the BioNER task. For this reason, the present study evaluates three well-known NER algorithms (CRF, BiLSTM, BiLSTM-CRF) with respect to two corpora (DrugBank and MedLine) using two classic word embeddings, GloVe Common Crawl (of the general type) and Pyysalo PM + PMC (specific), as unique features. Furthermore, three contextualized word embeddings (ELMo, Pooled Flair, and Transformer) are compared in their general and specific versions. The aim is to determine whether general embeddings can perform better than specialized ones on the BioNER task. To this end, four experiments were designed. In the first, we set out to identify the combination of classic word embedding, NER algorithm, and corpus that results in the best performance. The second evaluated the effect of the size of the corpus on performance. The third assessed the semantic cohesiveness of the classic word embeddings and their correlation with respect to several gold standards; while the fourth evaluates the performance of general and specific contextualized word embeddings on the BioNER task. Results show that the classic general word embedding GloVe Common Crawl performed better in the DrugBank corpus, despite having less word coverage and a lower internal semantic relationship than the classic specific word embedding, Pyysalo PM + PMC; while in the contextualized word embeddings the best results are presented in the specific ones. We conclude, therefore, when using classic word embeddings as features on the BioNER task, the general ones could be considered a good option. On the other hand, when using contextualized word embeddings, the specific ones are the best option.
| S-EPMC7959609 | biostudies-literature
Project description:BackgroundWord embeddings are dense numeric vectors used to represent language in neural networks. Until recently, there had been no publicly released embeddings trained on clinical data. Our work is the first to study the privacy implications of releasing these models.ObjectiveThis paper aims to demonstrate that traditional word embeddings created on clinical corpora that have been deidentified by removing personal health information (PHI) can nonetheless be exploited to reveal sensitive patient information.MethodsWe used embeddings created from 400,000 doctor-written consultation notes and experimented with 3 common word embedding methods to explore the privacy-preserving properties of each.ResultsWe found that if publicly released embeddings are trained from a corpus anonymized by PHI removal, it is possible to reconstruct up to 68.5% (n=411/600) of the full names that remain in the deidentified corpus and associated sensitive information to specific patients in the corpus from which the embeddings were created. We also found that the distance between the word vector representation of a patient's name and a diagnostic billing code is informative and differs significantly from the distance between the name and a code not billed for that patient.ConclusionsSpecial care must be taken when sharing word embeddings created from clinical texts, as current approaches may compromise patient privacy. If PHI removal is used for anonymization before traditional word embeddings are trained, it is possible to attribute sensitive information to patients who have not been fully deidentified by the (necessarily imperfect) removal algorithms. A promising alternative (ie, anonymization by PHI replacement) may avoid these flaws. Our results are timely and critical, as an increasing number of researchers are pushing for publicly available health data.
| S-EPMC7391163 | biostudies-literature