Background and research questions

Go to my homepage cc.oulu.fi/~scoats to follow these slides (explore the interactive elements!)

Online language and gender: Small but significant differences in feature frequencies have been observed (e.g. Argamon et al. 2007, Bamman et al. 2014, Coats 2016)

English profanity: Males use more overall (Mehl & Pennebaker 2003) and on Twitter (Bamman et al. 2014, Wang et al. 2014); males use stronger profanities (McEnery 2006)
How is profanity (English and Nordic-language) used on Twitter in the Nordic countries?
Goals are to:

Explore extent of profanity use by gender
Quantify results by country and gender and identify most characteristic words
Use word embeddings to investigate semantic space by gender

Data collection | Twitter Streaming API

3.3m tweets from Greenland, Iceland, Faroe Islands, Norway, Denmark, Åland, and Finland collected from the Twitter Streaming API 9 November 2016 – 5 June 2017 using Tweepy (Roesslein 2015)
From these “seed” tweets, identify male and female users, then download user timelimes (from REST API) of users with at least 10 tweets and at least 50% of tweets from a single Nordic country

Data collection | Gender disambiguation

Twitter users not required to specify gender (no attribute in profile provided for gender)
Tweets have an entity in which many users enter their real names, although it is not required (e.g. “Anna Hansson”)

Nordic Name Genderizer: Name frequency information for 15,406 names given to males and 17,856 names given to females obtained from Nordic statistical offices and used to induce a probability distribution for name gender

\[ \small P(name_x \in male) = \frac{\sum{name_x \in male}}{\sum{name_x}} ,\qquad P(name_x \in female) = \frac{\sum{name_x \in female}}{\sum{name_x}} \normalsize \]

author_name entity = “Anna Hansson” -> user classified as female
author_name entity = “!!!!ROCKER!!!!” -> ignored

Data collection | Twitter REST API

Of the 162,035 unique authors in the Nordic seed data, the method assigned gender to 102,513 users
Timelines (up to 3,250 tweets) downloaded from the Twitter REST API for gendered users with at least 10 tweets and \(\geq\) 50% of tweets from one Nordic country/territory
Final data for analysis consists of 26,926,653 tweets by 20,071 users comprising 344,347,287 word tokens

Tweet density by language

Map polygons from Natural Earth, maps from Open Street Maps

Some Sample Tweets containing Profanity

Profanity

Lexical-item-based approach
Six “core” taboo words in English treated as combinatorial elements

shit, fuck, cunt, whore, damn, nigger
Regex captures any items containing these strings, such as dumbshit, shithead, fucktard etc.

920 potentially offensive English words/n-grams (with optional plural ending)

E.g. bollocks, faggot, fuq, heeb, hell, hillbilly, homo, honkey, hussy, jackass, jackoff, jigaboo, lameass, lardass, lesbo, lezzie, limey, limpdick, mcfagget, minge, moon cricket, nignog, paki, pansy, peckerhead, pikey, piss, pussy, spastic, snow nigger, twat, white trash, wtf, etc.

748 potentially offensive Nordic words/n-grams from Greenlandic, Icelandic, Faroese, Norwegian, Danish, Swedish and Finnish (some with morphological variants)

E.g. arnapalaaq, iteq, nipangerit, aumingi, böllur, djöfullinn, drusla, fífl, fíflingur, mogghøvd, skitni fæni, pupp, pæss, rass, rasshøl, rompe, ronk, runk, ræv, ræva, rævhøl, rævva, bøsserøv, fisse, fissehår, hestepik, klaphat, kussekryller, lort, fitta, fittig, för helvete, helvete, jävlä, jävlar, knulla, kuk, kuksås, huoraa, huorilta, huorilla, huorille, huorista, huorien, huoriin, huorissa, huorat, huoria, kusipäät, kusipäältä, kusipäällä, etc.

Sources of Profanity

English:

Noswearing.com scrape (347 terms)
list of 1,383 potentially offensive terms created at Carnegie Mellon University, Pittsburgh, USA

Edited list to retain crude/vulgar/offensive lexical items referring mainly to bodily processes, sexuality, and race/ethnicity
Nordic languages:

Online word lists from software tools created to filter user input on websites (here and here for Norwegian, Finnish, Swedish and Danish)
Crowd-sourced Youswear dictionary for some terms in Icelandic, Faroese, and Greenlandic

Issue: Character sequences that are profanities in one language but normal words in another (slut, ho, fag, fart, dust, skit, olla, mutta, etc.)
Approach: Remove most short words that are non-profanities in other Nordic languages or English from the profanity dictionaries

Use of profanity by country and gender

For each country, the frequency of each of the 920 English profanities and 748 Nordic profanities was aggregated according to gender
The log-likelihood measure G was used to compare the relative frequency of the items by gender

\[ G = 2\sum_{i} {O_{i} \cdot \ln\left(\frac{O_i}{E_i}\right)} \]

Items with high G scores (low p-values) are used much more or much less by one gender
Starting with Nordic lexical items

Iceland (Nordic profanity)

Total Nordic-language profanity per 1k words: Females 0.204, males 0.224

Norway (Nordic profanity)

Total Nordic-language profanity per 1k words: Females 0.311, males 0.343

Denmark (Nordic profanity)

Total Nordic-language profanity per 1k words: Females 0.188, males 0.181

Sweden (Nordic profanity)

Total Nordic-language profanity per 1k words: Females 0.198, males 0.235

Finland (Nordic profanity)

Total Nordic-language profanity per 1k words: Females 0.478, males 0.602

Totals, all Nordics (Nordic profanity)

Total Nordic-language profanity per 1k words: Females 0.232, males 0.297 (Includes Greenland, Faroes, and Åland)

What about English lexical items?

Iceland (English profanity)

Total English-language profanity per 1k words: Females 2.952, males 3.392

Norway (English profanity)

Total English-language profanity per 1k words: Females 2.33, males 1.182

Denmark (English profanity)

Total English-language profanity per 1k words: Females 2.907, males 2.169

Sweden (English profanity)

Total English-language profanity per 1k words: Females 1.842, males 1.475

Finland (English profanity)

Total English-language profanity per 1k words: Females 1.498, males 1.271

Total, all Nordics (English profanity)

Total English-language profanity per 1k words: Females 2.028, males 1.627 (includes Greenland, Faroes, and Åland)

Profanity frequency by country and gender

Word embeddings

Linguistic elements that show similar collocational and syntactic distributions often exhibit similar semantics
“You shall know a word by the company it keeps” (Firth 1957)
Word embedding algorithms can be used to model semantic relationships based on the co-occurrence of lexical items within specified word spans

v(King) - v(Man) + v(Woman) = a value very close to v(Queen)

(Mikolov et al. 2013: 749)

Drawing

t-SNE to 2-dimensional space

Each word type in the data was converted to a vector with 400 dimensions
t-Distributed Stochastic Neighbor Embedding is used to reduce the 400-dimensional word vector space to two dimensions for visualization
The algorithm calculates the probabilities that any two word vectors are near to one another in high-dimensional space, then uses the t-distribution to capture the resulting probability distributions in lower-dimensional space
Words, including profanities, are now grouped according to similarity of context (and meaning)
Let’s compare males and females

t-SNE Visualization

Blue: 10,000 frequent words (out of the 893,473 unique types in the data). Red: The 402 (of 920) English profanity types that occurred at least once. Green: The 282 (of 748) Nordic profanity types that occurred at least once.

Caveats and future outlook

Results not necessarily representative of persons from these countries overall
Method for selecting items to be included in profanity lists can be improved (comparability of lists, morphological variants)
More comparisons possible (diachronic, language-specific, conversation-specific)
More sophisticated regex to capture more non-standard variants (b1tch,bi7tch,b.i.t.c.h.,b-i-t-c-h,b.1.t.c.h.,ßitch, etc.)
Quantify average distance from vocabulary core for different types of profanity

Preliminary summary and conclusions

Males use more Nordic-language profanities
Females more English-language profanities

If we consider that: Females use more affect words in general (Newman et al. 2008) and in English-language Twitter from the US (Bamman et al. 2014)
Less “emotional force” is associated with taboo language by L2 speakers (Dewaele 2004, Eilola and Havelka 2010)
For Nordic females, English-language profanities have been “deprofanitized” - they are simply affect words
Profanities in the Nordic languages, however, still exert taboo
The multilingual semantic space suggests a functional and communicative separation by gender for some items

Thank you for your attention!

Acknowledgements

Also thanks to

Dorthe Larsen (Danmarks Statistik) for Danish name lists
Joar Skott (Statistika centralbyrån, Sweden) for Swedish name lists
Finland’s Center for Scientific Computing for data storage and computing resources

References

Argamon, S., M. Koppel, J. W. Pennebaker and J. Schler. 2007. Mining the blogosphere: Age, gender, and the varieties of self-expression. First Monday 12/9. http://firstmonday.org/ojs/index.php/fm/article/view/2003/1878

Bamman, D., J. Eisenstein and T. Schnoebelen. 2014. Gender identity and lexical variation in social media. Journal of Sociolinguistics 18(2), 135–160. http://onlinelibrary.wiley.com/doi/10.1111/josl.12080/full

Coats, S. 2016. Grammatical feature frequencies of English on Twitter in Finland. In L. Squires (ed.), English in computer-mediated communication: Variation, representation, and change. Berlin: De Gruyter. 179–210.

Dewaele, J.-M. 2004. The emotional force of swearwords and taboo words in the speech of multilinguals. Journal of Multilingual and Multicultural Development 25(2–3), 204–222.

Firth, J.R. 1957. Papers in linguistics, 1934–1951. London: Oxford University Press.

Labov, W. 1990. The intersection of sex and social class in the course of linguistic change. Language Variation and Change 2, 205–254.

Lui, M. and T. Baldwin. 2012. Langid.py: An off-the-shelf language identification tool. 50th Proceedings of the Association for Computational Linguistics, 25–30. Stroudsburg, PA: ACL. http://dl.acm.org/citation.cfm?id=2390475

McEnery, T. 2006. Swearing in English: Bad language, purity and power from 1586 to the present. New York: Routledge.

Mehl, M. and J. Pennebaker. 2003. The sounds of social life: A psychometric analysis of students’ daily social environments and natural conversations. Journal of Personality and Social Psychology 84(4), 857–870.

Mikolov, T., W. Yih, and G. Zweig. 2013. Linguistic regularities in continuous space word represen-tations. In: Proceedings of HLT-NAACL 13, 746–751. https://www.aclweb.org/anthology/N13-1090

Newman, M.L., C. Groom, L. Handelman, and J. Pennebaker. 2008. Gender differences in language use: An analysis of 14,000 text samples.Discourse Processes 45, 211–236. http://citeseerx.ist.psu.edu/viewdoc/download?doi=10.1.1.216.4267&rep=rep1&type=pdf

Roesslein, J. 2015. Tweepy. Python package [Computer software]. http://www.tweepy.org

Wang, W., L. Chen, K. Thirunarayan, and A. P. Sheth. 2014. Cursing in English on Twitter. In: Proceedings of the 17th ACM conference on Computer supported cooperative work & social computing, 415–425.

Profanity on Twitter in the Nordics