Joshua Conrad Jackson

Social media often feels saturated with politics and morality - but is that feeling accurate? Our new paper finds that moralization has increased markedly on social media from 2013-2021, more than traditional media. See 🧵 below!

One of the largest-scale analyses of historical text data that I have contributed to

The finding: language on social media has become more moralized over the 21st century; we don't see the same trends on news media

Kudos to the first author @curtispuryear.bsky.social on the enormous effort

Alex Koch contributed endless theoretical insights over two years

Tessa Charlesworth gave some of the most useful and thorough comments I have ever read

And @andyluttrell.bsky.social pushed this paper to the point it is now

I also want to recognize the authors once more:

@yuanzeliu.bsky.social completed this massive project as a pre-doc, which speaks to his promise as a scholar

Our general discussion covers this framework in great depth, and uses it to make tentative inferences about all of our findings

This is a working paper, so any feedback would be helpful!

- When social dilemmas change, trait language changes -

Example: The rising division of labor over the last 200 years has meant that people are selected on specific competences

This might be one reason why agency language has become more semantically heterogeneous

- We use trait words as diagnostic tools for prediction -

Example: We may have many negative communal words because cooperation is common, so it is more diagnostic to communicate about deviations from cooperation

But since skill is rare in most domains, we have many positive words about agency

- Trait words reflect the nature of social dilemmas -

Example: We view three of the FACT dimensions as mapping onto classic social dilemmas identified in game theory

-Communion ➡️ cooperation
-Traditionalism ➡️ coordination
-Agency ➡️ whether people can cooperate and coordinate

Our approach makes several simple assumptions that encompass our different findings

1. Trait words reflect the nature of social dilemmas

2. We use trait words as diagnostic tools for prediction in these dilemmas

3. When social dilemmas change, we also change our trait language

The general discussion of our paper reviews these findings using a new “functional constructionist” approach to trait words, building on past work in emotion

Functional ➡️ trait words are useful
Constructionist ➡️ There is no single trait space

We find that communion words are converging in semantic space—extending work on the collapse of morality into a single dimension (cdr.lib.unc.edu/downloads/g7...)

But words about agency/competence are diverging in semantic space. They are becoming less related to each other over time

We also see interesting trends in the semantic coherence of these factors

We calculate coherence by looking at clustering in semantic space over time from word embeddings

Here are clusters of words projected based on their 19th and 20th century embeddings

The small change we do see is a surge of “traditionalism” words around the rise of participatory democracies in Europe

“Conservativism-liberalism” is the “youngest” trait dimension by date of introduction

Finally, we look at the history of trait words using dates of origin from the Oxford English Dictionary

This plot shocked me – our trait vocabulary has been remarkably stable over time

We have always had more words about communion and the fewest words about fitness

Negative and positive words are also vary in their specificity.

Negative are more likely to be specific, whereas positive words are more likely to generalize across many dimensions

Are there more negative or positive trait words? I once assumed there were more negative words because of negativity dominance

The real story is complicated

Communion dimensions are indeed filled with negative words.

But we have more positive words about agency, traditionalism, and fitness

Most trait dimensions are evaluative – the have positively and negatively valenced poles (it is good to be friendly and bad to be unfriendly)

But some dimensions are not. Communion and agency are more evaluative than traditionalism or fitness dimensions

For example, we find that Communion words are highly clustered (eg. words expressing friendliness tend to also express morality)

But words about traditionalism are spread across the network, closely knit with communion and agency

Although this FACT model is interesting and parsimonious, it masks variation within factors, and links between factors

The network below shows all words connected by their overlapping semantics.

The FACT factors partly organize the network, but lots of complexity remains

In an EFA, these 24 dimensions reduced to a four-dimension FACT model

Fitness (e.g., Attractiveness)
Agency (e.g., Assertiveness)
Communion (e.g., Morality)
Traditionalism (e.g., Conservatism)

Our model contains parts of prior models, most notably the ABC model of social evaluation

After collecting the words, we turned to their semantic structure

We took 24 dimensions from a review of personality and psych science lit. Then Prolific workers rated all words on these dimensions

This plot shows how some words are generalized (relevant to many dimensions); others are specific

One observation from building this list is that being a “trait word” is not black and white

Traits are natural categories with fluid boundaries. Some words are almost exclusively used as traits, but many have multiple meanings

Our approach gives words a continuous probability of being traits

We host this trait list on our OSF page (osf.io/7k4yj/files/...), freely available to all

All traits are linked to:
-A definition
-Probability of being a trait word
-Loading on 24 dimensions (e.g., friendliness, openness)
-Date of origin
-Number of meanings

To create our list, we...

a) Fine-tuned and validated BERT models to be high-quality "trait detectors"

b) Used these models to annotate the entire vocabulary of Google Books

c) Checked these annotations using another LLM (GPT)

This process gave us 2847 trait words

The main goal of our paper was to create a new theoretical framework for understanding trait language (expanded later)

To do so, we decided to create a large and high-quality list of English trait words, something that psychologists have tried to do since the classic work of Allport and Galton

English language is filled with trait words like “caring” and “smart”

These words are the currency of personality/social psych, yet key questions remain about their evolution, function, and structure

We take on these questions in a preprint led by @yuanzeliu.bsky.social
osf.io/preprints/ps...

Look what you could publish (anonymously) in Nature in 1970.

If anyone is submitting to SESP and looking for a speaker to complete their symposium, I have a collaborator doing really interesting work related to culture, income, and social cognition. He has multiple cool projects on all of those topics.

Feel free to message me and I can connect you

I'm disappointed to share that my NSF career grant on anti-Asian dehumanization was terminated. This affects ongoing project activities, which have shown great progress so far, and support for my research team and more.

I'm sad to share that the hiring of the postdoc role is currently on pause.

This paper is now published. www.nature.com/articles/s44...