Profanity on Twitter in the Nordics

Steven Coats
English Philology, University of Oulu
steven.coats@oulu.fi

5th SwiSca Symposium on Swearing
November 23rd, 2017

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

Profanity on Twitter in the Nordics

Background and research questions

Data collection | Twitter Streaming API

Data collection | Gender disambiguation

Data collection | Twitter REST API

Tweet density by language