[Paper Review] Quantifying language changes surrounding mental health on Twitter

Anne Marie Stupinski, Thayer Alshaabi+6 more|arXiv (Cornell University)|Jun 2, 2021

Mental Health via Writing36 references4 citations

TL;DR

This study analyzes 10% of English-language tweets from 2012 to 2018 to quantify shifts in language around mental health, using n-grams and sentiment analysis. It finds a nearly 100-fold increase in mentions of 'mental health,' rising social amplification via retweets, and declining positivity in associated content, indicating growing awareness and reduced stigma over time.

ABSTRACT

Mental health challenges are thought to afflict around 10% of the global population each year, with many going untreated due to stigma and limited access to services. Here, we explore trends in words and phrases related to mental health through a collection of 1- , 2-, and 3-grams parsed from a data stream of roughly 10% of all English tweets since 2012. We examine temporal dynamics of mental health language, finding that the popularity of the phrase 'mental health' increased by nearly two orders of magnitude between 2012 and 2018. We observe that mentions of 'mental health' spike annually and reliably due to mental health awareness campaigns, as well as unpredictably in response to mass shootings, celebrities dying by suicide, and popular fictional stories portraying suicide. We find that the level of positivity of messages containing 'mental health', while stable through the growth period, has declined recently. Finally, we use the ratio of original tweets to retweets to quantify the fraction of appearances of mental health language due to social amplification. Since 2015, mentions of mental health have become increasingly due to retweets, suggesting that stigma associated with discussion of mental health on Twitter has diminished with time.

Motivation & Objective

• To quantify changes in language surrounding mental health on Twitter from 2012 to 2018.
• To examine temporal trends in the popularity and sentiment of mental health-related phrases.
• To assess the role of social amplification (retweets) in spreading mental health discourse.
• To investigate how public events and awareness campaigns influence language trends.
• To evaluate shifts in positivity and stigma associated with mental health discussions.

Proposed method

• The study analyzes a 10% sample of English tweets from 2012 to 2018, extracting 1-, 2-, and 3-grams centered on the term 'mental health'.
• It uses n-gram frequency analysis to track the rising popularity of 'mental health' and related phrases over time.
• Sentiment analysis is applied to measure ambient happiness in tweets containing 'mental health' to assess emotional tone.
• The ratio of retweets to original tweets is calculated to quantify social amplification of mental health content.
• Temporal spikes are correlated with known events such as mental health awareness days, celebrity suicides, and mass shootings.
• A new dataset of n-grams from tweets mentioning 'mental health' is compiled to analyze evolving language patterns.

Experimental results

Research questions

• RQ1 How has the frequency of the phrase 'mental health' changed on Twitter between 2012 and 2018?
• RQ2 What role do social media amplification (retweets) and original content play in spreading mental health discourse?
• RQ3 How has the sentiment or positivity of tweets mentioning 'mental health' evolved over time?
• RQ4 What external events trigger spikes in mental health-related discussions on Twitter?
• RQ5 To what extent has the language around mental health become more normalized or stigmatized over the past decade?

Key findings

• The phrase 'mental health' increased in popularity by nearly two orders of magnitude between 2012 and 2018.
• Mentions of 'mental health' spike annually due to awareness campaigns and unpredictably in response to tragedies like mass shootings and celebrity suicides.
• The positivity of tweets containing 'mental health' has declined in recent years, despite overall growth in discussion.
• Since 2015, a growing proportion of mental health mentions have come from retweets, indicating increased social amplification and reduced stigma.
• The language of mental health discourse has evolved, with new topics emerging post-2020, particularly related to pandemic-related distress.
• The study identifies a shift from personal, self-disclosing content to more institutional and awareness-driven messaging, especially from organized accounts.